Arrow Research search

Author name cluster

Dong Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

74 papers
2 author rows

Possible papers

74

EAAI Journal 2026 Journal Article

A velocity-prediction lightweight diffusion model for three-dimensional aircraft aerodynamic inverse design

  • Jia-hao Lin
  • Shu-sheng Chen
  • Jin-ping Li
  • Quan-feng Jiang
  • Mu-liang Jia
  • Dong Li
  • Yue-qing Wang

The work devises a novel velocity-prediction lightweight diffusion model (VPLDM) for three-dimensional aircraft aerodynamic inverse design under high-dimensional variable constraints. The model uses a lightweight diffusion modeling paradigm based on a multilayer perceptron, and reconstructs the noise predictions of traditional diffusion models into velocity predictions, which improves the design efficiency and design accuracy. Trained on a dataset of three-dimensional aircraft, the model is able to generate new samples from random vectors that meet the constraints of specific aerodynamic performance indicators. VPLDM achieves higher design accuracy while demonstrating approximately 4 times higher sampling efficiency compared to Denoising Diffusion Probabilistic Model. The model can also generate aircraft schemes with significantly different geometries in the design space, which confirms the typical non-uniqueness of solutions to the aerodynamic inverse design problem for aircraft. All generated shapes satisfy the desired aerodynamic characteristics, demonstrating the role of VPLDM in the three-dimensional aircraft aerodynamic inverse design.

Details DOI

AAAI Conference 2026 Conference Paper

CL-DMDF: Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

  • Dong Li
  • Lingling Zhang
  • Binghao Han
  • Linlin Ding
  • Yue Kou

Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patterns, thereby enhancing data processing and decision-making. While existing methods for structured multimodal inputs are typically designed around specific tasks and assume fully observed modalities, realworld applications often suffer from uncertain or missing modality inputs due to various factors. Some traditional models overly emphasize local interactions within missing modalities, neglecting the global complementary cues embedded in multimodal representations. To overcome these limitations, we propose a Dynamic Multimodal Data Fusion model based on Contrastive Learning (CL-DMDF). CL-DMDF introduces a novel attention mechanism that operates across both feature and modality dimensions to compute reliable attention scores, effectively reflecting importance at each level. The CL-DMDF further incorporates an entity-centroid contrastive learning module that constructs centroid-based positive samples from entity features to enhance discriminative learning. Additionally, an adaptive fusion module is employed to improve the efficiency and accuracy of dynamic fusion strategies. Extensive experiments conducted on three datasets demonstrate the effectiveness of the CL-DMDF across diverse multimodal fusion tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring

  • Mingchen Zhong
  • Xin Lu
  • Dong Li
  • Senyan Xu
  • Ruixuan Jiang
  • Xueyang Fu
  • Baocai Yin

Low-light video deblurring poses significant challenges in applications like nighttime surveillance and autonomous driving due to dim lighting and long exposures. While event cameras offer potential solutions with superior low-light sensitivity and high temporal resolution, existing fusion methods typically employ staged strategies, limiting their effectiveness against combined low-light and motion blur degradations. To overcome this, we propose CompEvent, a complex neural network framework enabling holistic full-process fusion of event data and RGB frames for enhanced joint restoration. CompEvent features two core components: 1) Complex Temporal Alignment GRU, which utilizes complex-valued convolutions and processes video and event streams iteratively via GRU to achieve temporal alignment and continuous fusion; and 2) Complex Space-Frequency Learning module, which performs unified complex-valued signal processing in both spatial and frequency domains, facilitating deep fusion through spatial structures and system-level characteristics. By leveraging the holistic representation capability of complex-valued neural networks, CompEvent achieves full-process spatiotemporal fusion, maximizes complementary learning between modalities, and significantly strengthens low-light video deblurring capability. Extensive experiments demonstrate that CompEvent outperforms SOTA methods in addressing this challenging task.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation

  • Jiajun Jiao
  • Haowei Zhu
  • Puyuan Yang
  • Jianghui Wang
  • Ji Liu
  • Ziqiong Liu
  • Dong Li
  • Yuejian Fang

Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real-world deployment. Accelerating diffusion models is therefore essential, yet determining how to combine multiple model acceleration techniques remains a significant challenge. To address this issue, we introduce a framework driven by large language models (LLMs) for automated acceleration code generation and evaluation. First, we present DiffBench, a comprehensive benchmark that implements a three stage automated evaluation pipeline across diverse diffusion architectures, optimization combinations and deployment scenarios. Second, we propose DiffAgent, an agent that generates optimal acceleration strategies and codes for arbitrary diffusion models. DiffAgent employs a closed-loop workflow in which a planning component and a debugging component iteratively refine the output of a code generation component, while a genetic algorithm extracts performance feedback from the execution environment to guide subsequent code refinements. We provide a detailed explanation of the DiffBench construction and the design principles underlying DiffAgent. Extensive experiments show that DiffBench offers a thorough evaluation of generated codes and that DiffAgent significantly outperforms existing LLMs in producing effective diffusion acceleration strategies.

PDF Details DOI

AAAI Conference 2026 Conference Paper

FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting

  • Chao Gong
  • Dong Li
  • Yingwei Pan
  • Jingjing Chen
  • Ting Yao
  • Tao Mei

Text-guided image inpainting endeavors to generate new content within specified regions of images using textual prompts from users. The primary challenge is to accurately align the inpainted areas with the user-provided prompts while maintaining a high degree of visual fidelity. While existing inpainting methods have produced visually convincing results by leveraging the pre-trained text-to-image diffusion models, they still struggle to uphold both prompt alignment and visual rationality simultaneously. In this work, we introduce FreeInpaint, a plug-and-play tuning-free approach that directly optimizes the diffusion latents on the fly during inference to improve the faithfulness of the generated images. Technically, we introduce a prior-guided noise optimization method that steers model attention towards valid inpainting regions by optimizing the initial noise. Furthermore, we meticulously design a composite guidance objective tailored specifically for the inpainting task. This objective efficiently directs the denoising process, enhancing prompt alignment and visual rationality by optimizing intermediate latents at each step. Through extensive experiments involving various inpainting diffusion models and evaluation metrics, we demonstrate the effectiveness and robustness of our proposed FreeInpaint.

PDF Details DOI

AAAI Conference 2026 Conference Paper

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

  • Jian Zhao
  • Runze Liu
  • Kaiyan Zhang
  • Zhimu Zhou
  • Junqi Gao
  • Dong Li
  • Jiafei Lyu
  • Zhouyi Qian

Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence on scalar value prediction without leveraging the generative abilities of LLMs, and (3) inability to scale the test-time compute of PRMs. In this work, we introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification before providing judgment for each reasoning step. To obtain high-quality process supervision labels and rationale data, we propose Relative Progress Estimation (RPE) and a rationale synthesis framework that incorporates code verification. Experimental results on ProcessBench and several mathematical reasoning tasks show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset. Through test-time scaling, a 1.5B GenPRM outperforms GPT-4o, and a 7B GenPRM surpasses Qwen2.5-Math-PRM-72B on ProcessBench. Additionally, GenPRM demonstrates strong abilities to serve as a critic model for policy model refinement. This work establishes a new paradigm for process supervision that bridges the gap between PRMs and critic models in LLMs.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Learnable Permutation for Structured Sparsity on Transformer Models

  • Zekai Li
  • Ji Liu
  • Guanchen Li
  • Yixing Xu
  • Ziqiong Liu
  • Xuanwu Yin
  • Dong Li
  • Emad Barsoum

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further improve post-pruning performance is weight permutation, which reorders model weights into patterns more amenable to pruning. However, the exponential growth of the permutation search space with the scale of Transformer architectures forces most methods to rely on greedy or heuristic algorithms, limiting the effectiveness of reordering. In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost matrix to quantify the cost of swapping any two input channels of a given weight matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation matrix given a cost matrix, and a sparsity optimization loss function to directly optimize the permutation operator. We extensively validate our approach on vision and language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity.

PDF Details DOI

AAAI Conference 2026 Conference Paper

LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs

  • Xiaoxu Ma
  • Dong Li
  • Minglai Shao
  • Xintao Wu
  • Chen Zhao

Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with the goal of maintaining accurate node classification while simultaneously identifying OOD nodes. We propose a novel approach, LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (LECT), which integrates large language models (LLMs) and energy-based contrastive learning. The proposed method involves generating high-quality OOD samples by leveraging the semantic understanding and contextual knowledge of LLMs to create dependency-aware pseudo-OOD nodes, and applying contrastive learning based on energy functions to distinguish between in-distribution (IND) and OOD nodes. The effectiveness of our method is demonstrated through extensive experiments on six benchmark datasets, where our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery

  • Dong Li
  • Zhengzhang Chen
  • Xujiang Zhao
  • Linlin Yu
  • Zhong Chen
  • Yi He
  • Haifeng Chen
  • Chen Zhao

Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi-agent RL-based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real-valued space to the DAG space as an intra-batch strategy, then incorporates two RL agents—state-specific and state-invariant—to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN outperforms state-of-the-art methods in terms of both efficiency and effectiveness.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models

  • Zhixia He
  • Chen Zhao
  • Minglai Shao
  • Xintao Wu
  • Xujiang Zhao
  • Dong Li
  • Qin Tian
  • Linlin Yu

Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection performance by integrating both visual and textual modalities. In this context, negative prompts are introduced to emphasize the dissimilarity between image features and prompt content. However, these prompts often include a broad range of non-ID features, which may result in suboptimal outcomes due to the capture of overlapping or misleading information. To address this issue, we propose Positive and Negative Prompt Supervision, which encourages negative prompts to capture inter-class features and transfers this semantic knowledge to the visual modality to enhance OOD detection performance. Our method begins with class-specific positive and negative prompts initialized by large language models (LLMs). These prompts are subsequently optimized, with positive prompts focusing on features within each class, while negative prompts highlight features around category boundaries. Additionally, a graph-based architecture is employed to aggregate semantic-aware supervision from the optimized prompt representations and propagate it to the visual branch, thereby enhancing the performance of the energy-based OOD detector. Extensive experiments on two benchmarks, CIFAR-100 and ImageNet-1K, across eight OOD datasets and five different LLMs, demonstrate that our method outperforms state-of-the-art baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning

  • Huanxuan Liao
  • Yixing Xu
  • Shizhu He
  • Guanchen Li
  • Xuanwu Yin
  • Dong Li
  • Emad Barsoum
  • Jun Zhao

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address this issue by compressing the KV cache along the temporal axis through strategies such as token eviction or merging to reduce memory and computational overhead. However, these methods often neglect fine-grained importance variations across feature dimensions (i.e., the channel axis), thereby limiting their ability to effectively balance efficiency and model accuracy. In reality, we observe that channel saliency varies dramatically across both queries and positions: certain feature channels carry near-zero information for a given query, while others spike in relevance. To address this oversight, we propose SPARK, a training-free plug-and-play method that applies unstructured sparsity by pruning KV at the channel level, while dynamically restoring the pruned entries during attention score computation. Notably, our approach is orthogonal to existing KV compression and quantization techniques, making it compatible for integration with them to achieve further acceleration. By reducing channel-level redundancy, SPARK enables processing of longer sequences within the same memory budget. For sequences of equal length, SPARK not only preserves or improves model accuracy but also reduces KV cache storage by over 30% compared to eviction-based methods. Furthermore, even in an aggressive pruning ratio of 80%, SPARK maintains performance with less degradation than 5% compared to the based eviction method, demonstrating robustness and effectiveness. Our code will be available at \url{https://github.com/AMD-AIG-AIMA/AMD-Spark}.

PDF Details DOI

AAAI Conference 2025 Conference Paper

A Lottery Ticket Hypothesis Approach with Sparse Fine-tuning and MAE for Image Forgery Detection and Localization

  • Jiaying Zhu
  • Dong Li
  • Xueyang Fu
  • Gege Shi
  • Jie Xiao
  • Aiping Liu
  • Zheng-Jun Zha

The rise in sophisticated image forgery techniques, driven by advancements in image editing and generation, has posed new security challenges. Traditional methods, designed for specific tampering artifacts, struggle with out-of-distribution image forgery detection. In this paper, we propose a shift in paradigm, placing greater emphasis on the universal characteristics of authentic images, as opposed to solely focusing on specific forgery signals. We introduce an enhancement to the Masked Autoencoder (MAE), aptly termed the Forgery MAE (FMAE). This modification retains the inherent characteristics of natural images while integrating multi-source forgery information. Our implementation involves applying the lottery ticket hypothesis during pre-training to identify forgery-sensitive parameters, followed by their sparse fine-tuning to target the forgery detection and localization task. Concurrently, we develop a ``mixture of experts'' noise extractor to compile multi-source forgery data. Our FMAE effectively extracts forgery features and shows strong resilience against unseen forgeries. Extensive experiments across multiple datasets confirm our method's superior accuracy and generalization capability over existing techniques.

PDF Details DOI

EAAI Journal 2025 Journal Article

A Multi-scale Patch Mixer Network for Time Series Anomaly Detection

  • Qiushi Wang
  • Yueming Zhu
  • Zhicheng Sun
  • Dong Li
  • Yunbin Ma

With the development of Internet of Things (IoT) technology, a large amount of data with temporal characteristics is collected and stored. How to efficiently and accurately identify anomalies from these data is a major challenge. At present, there are many problems in the application of anomaly detection, including non-stationary data, complex and difficult-to-collect anomalies, the need for real-time detection and the limitation of computing resources. But few methods can comprehensively consider these issues. To overcome these challenges, we propose a lightweight neural network, Multi-scale Patch Mixer Network (MP-MixerNet). It is mainly composed of a Mixer Block based on fully connected layer design, which contains a Temporal-Mixer and a Spatial-Mixer, and can simultaneously model the intra- and inter-series dependencies of multivariate time series. We also perform multi-scale patch segmentation based on frequency analysis, which helps the model extract robust features from multiple period views. In addition, we design an Input Stabilization module to help the model deal with data distribution shift. Experimental results on a public time series anomaly detection dataset show that we are able to achieve higher comprehensive performance with fewer parameters and inference time.

Details DOI

NeurIPS Conference 2025 Conference Paper

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

  • 俊琪 高
  • Zhichang Guo
  • Dazhi Zhang
  • Dong Li
  • Runze Liu
  • Pengfei Li
  • Kai Tian
  • Biqing Qi

Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. While promising, existing methods suffer from two major limitations: 1) reliance on real data from limited domain for knowledge fusion, preventing the target LLM from fully acquiring knowledge across diverse domains, and 2) fixed data allocation proportions across domains, failing to dynamically adjust according to the target LLM's varying capabilities across domains, leading to a capability imbalance. To overcome these limitations, we propose Bohdi, a synthetic-data-only heterogeneous LLM fusion framework. Through the organization of knowledge domains into a hierarchical tree structure, Bohdi enables automatic domain exploration and multi-domain data generation through multi-model collaboration, thereby comprehensively extracting knowledge from source LLMs. By formalizing domain expansion and data sampling proportion allocation on the knowledge tree as a Hierarchical Multi-Armed Bandit problem, Bohdi leverages the designed DynaBranches mechanism to adaptively adjust sampling proportions based on the target LLM's performance feedback across domains. Integrated with our proposed Introspection-Rebirth (IR) mechanism, DynaBranches dynamically tracks capability shifts during target LLM's updates via Sliding Window Binomial Likelihood Ratio Testing (SWBLRT), further enhancing its online adaptation capability. Comparative experimental results on a comprehensive suite of benchmarks demonstrate that Bohdi significantly outperforms existing baselines on multiple target LLMs, exhibits higher data efficiency, and virtually eliminates the imbalance in the target LLM's capabilities.

PDF Details

IJCAI Conference 2025 Conference Paper

CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness

  • Yingwei Zhang
  • Ke Bu
  • Zhuoran Zhuang
  • Tao Xie
  • Yao Yu
  • Dong Li
  • Yang Guo
  • Detao Lv

The past decades witness the significant advancements in time series forecasting (TSF) across various real-world domains, including e-commerce and disease spread prediction. However, TSF is usually constrained by the uncertainty dilemma of predicting future data with limited past observations. To settle this question, we explore the use of Cross-Future Behavior (CFB) in TSF, which occurs before the current time but takes effect in the future. We leverage CFB features and propose the CRoss-Future Behavior Awareness based Time Series Forecasting method (CRAFT). The core idea of CRAFT is to utilize the trend of cross-future behavior to mine the trend of time series data to be predicted. Specifically, to settle the sparse and partial flaws of cross-future behavior, CRAFT employs the Koopman Predictor Module to extract the key trend and the Internal Trend Mining Module to supplement the unknown area of the cross-future behavior matrix. Then, we introduce the External Trend Guide Module with a hierarchical structure to acquire more representative trends from higher levels. Finally, we apply the demand-constrained loss to calibrate the distribution deviation of prediction results. We conduct experiments on real-world dataset. Experiments on both offline large-scale dataset and online A/B test demonstrate the effectiveness of CRAFT. Our dataset and code are available at https: //github. com/CRAFTinTSF/CRAFT.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DreamUHD: Frequency Enhanced Variational Autoencoder for Ultra-High-Definition Image Restoration

  • Yidi Liu
  • Dong Li
  • Jie Xiao
  • Yuanfei Bao
  • Senyan Xu
  • Xueyang Fu

Existing ultra-high-definition (UHD) image restoration methods often struggle with consistency due to downsampling. We aim to address these challenges by leveraging the powerful latent space representation and reconstruction capabilities of Variational Autoencoders (VAE). However, applying VAE to UHD image restoration presents challenges: 1) High-performing VAEs have large parameter sizes, leading to significant carbon footprints; 2) The self-reconstruction property of VAE hinders bridging the domain gap between clean and degraded images; 3) Latent encoding in VAE can lose high-frequency information, compromising image detail. To overcome these challenges, we propose a frequency enhanced VAE UHD image restoration framework by integrating frequency priors. First, we design the Fourier-based lightweight frequency learning within the VAE to improve parameter efficiency. Then, we introduce a wavelet-based adapter that extracts multi-scale image information and employs frequency-aware adaptive modulation to bridge the domain gap by integrating degraded image data into the pre-trained VAE. Additionally, the adapter injects high-frequency information into the VAE decoder, enhancing detail in the restored images. In this way, our method effectively combines the powerful latent space representation with frequency priors to enhance UHD image restoration. Extensive experiments on various UHD image restoration tasks show that our method surpasses state-of-the-art methods both qualitatively and quantitatively.

PDF Details DOI

AAAI Conference 2025 Conference Paper

EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene

  • Yixiong Huo
  • Guangfeng Jiang
  • Hongyang Wei
  • Ji Liu
  • Song Zhang
  • Han Liu
  • Xingliang Huang
  • Mingjie Lu

3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstructing driving scenes. However, these methods often rely on various types of data, such as depth maps, 3D bounding boxes, and trajectories of moving objects. Additionally, the lack of annotations for synthesized images limits their direct application in downstream tasks. To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations. EGSRAL enhances 3D GS's capability to model both dynamic objects and static backgrounds and introduces a novel adaptor for auto labeling, generating corresponding annotations based on existing annotations. We also propose a grouping strategy for vanilla 3D GS to address perspective issues in rendering large-scale, complex scenes. Our method achieves state-of-the-art performance on multiple datasets without any extra annotation. For example, the PSNR metric reaches 29.04 on the nuScenes dataset. Moreover, our automated labeling can significantly improve the performance of 2D/3D detection tasks.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

FADE: Towards Fairness-aware Data Generation for Domain Generalization via Classifier-Guided Score-based Diffusion Models

  • Yujie Lin
  • Dong Li
  • Minglai Shao
  • Guihong Wan
  • Chen Zhao

Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems, particularly in scenarios involving distribution shifts. Traditional methods for addressing fairness have failed in domain generalization due to their lack of consideration for distribution shifts. Although disentanglement has been used to tackle FairDG, it is limited by its strong assumptions. To overcome these limitations, we propose Fairness-aware Classifier-Guided Score-based Diffusion Models (FADE) as a novel approach to effectively address the FairDG issue. Specifically, we first pre-train a score-based diffusion model (SDM) and two classifiers to equip the model with strong generalization capabilities across different domains. Then, we guide the SDM using these pre-trained classifiers to effectively eliminate sensitive information from the generated data. Finally, the generated fair data is used to train downstream classifiers, ensuring robust performance under new data distributions. Extensive experiments on three real-world datasets demonstrate that FADE not only enhances fairness but also improves accuracy in the presence of distribution shifts. Additionally, FADE outperforms existing methods in achieving the best accuracy-fairness trade-offs.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Fast and Slow Gradient Approximation for Binary Neural Network Optimization

  • Xinquan Chen
  • Junqi Gao
  • Biqing Qi
  • Dong Li
  • Yiang Luo
  • Fangyuan Li
  • Pengfei Li

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.

PDF Details DOI

JMLR Journal 2025 Journal Article

From Sparse to Dense Functional Data in High Dimensions: Revisiting Phase Transitions from a Non-Asymptotic Perspective

  • Shaojun Guo
  • Dong Li
  • Xinghao Qiao
  • Yizhu Wang

Nonparametric estimation of the mean and covariance functions is ubiquitous in functional data analysis and local linear smoothing techniques are most frequently used. Zhang and Wang (2016) explored different types of asymptotic properties of the estimation, which reveal interesting phase transition phenomena based on the relative order of the average sampling frequency per subject $T$ to the number of subjects $n$, partitioning the data into three categories: “sparse”, “semi-dense”, and “ultra-dense”. In an increasingly available high-dimensional scenario, where the number of functional variables $p$ is large in relation to $n$, we revisit this open problem from a non-asymptotic perspective by deriving comprehensive concentration inequalities for the local linear smoothers. Besides being of interest by themselves, our non-asymptotic results lead to elementwise maximum rates of $L_2$ convergence and uniform convergence serving as a fundamentally important tool for further convergence analysis when $p$ grows exponentially with $n$ and possibly $T$. With the presence of extra $\log p$ terms to account for the high-dimensional effect, we then investigate the scaled phase transitions and the corresponding elementwise maximum rates from sparse to semi-dense to ultra-dense functional data in high dimensions. We also discuss a couple of applications of our theoretical results. Finally, numerical studies are carried out to confirm the established theoretical properties. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

ICRA Conference 2025 Conference Paper

GARAD-SLAM: 3D Gaussian Splatting for Real-Time Anti Dynamic SLAM

  • Mingrui Li
  • Weijian Chen
  • Na Cheng
  • Jingyuan Xu
  • Dong Li
  • Hongyu Wang

The 3D Gaussian Splatting (3DGS)-based SLAM system has garnered widespread attention due to its excellent performance in real-time high-fidelity rendering. However, in real-world environments with dynamic objects, existing 3DGS-based SLAM systems often face mapping errors and tracking drift issues. To address these problems, we propose GARAD-SLAM, a real-time 3DGS-based SLAM system tailored for dynamic scenes. In terms of tracking, unlike traditional methods, we directly perform dynamic segmentation on Gaussians and map them back to the front-end to obtain dynamic point labels through a Gaussian pyramid network, achieving precise dynamic removal and robust tracking. For mapping, we impose rendering penalties on dynamically labeled Gaussians, which are updated through the network, to avoid irreversible erroneous removal caused by simple pruning. Our results on real-world datasets demonstrate that our method is competitive in tracking compared to baseline methods, generating fewer artifacts and higher-quality reconstructions in rendering.

Details

TMLR Journal 2025 Journal Article

LASP: Linear Attention Sequence Parallelism

  • Weigao Sun
  • Zhen Qin
  • Dong Li
  • Xuyang Shen
  • Yu Qiao
  • Yiran Zhong

Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take advantage of their right-product-first feature, resulting in sub-optimal communication efficiency and usability. In this paper, we introduce Linear Attention Sequence Parallelism (LASP), an efficient SP approach designed for linear attention-based transformer models. Specifically, we design an efficient point-to-point ring-style communication mechanism to leverage the right-product kernel trick of linear attention, which sharply decreases the communication overhead, comparing with existing SP methods. We enhance the computation efficiency of LASP by performing kernel fusion and intermediate state caching, making the implementation of LASP hardware-friendly on GPUs. Furthermore, we meticulously ensure the compatibility of sequence-level LASP with all types of batch-level data parallel methods, which is vital for distributed training on large clusters with very-long sequences. We also discuss the generalization of LASP on other linear sequence modeling methods. Extensive experiments on linear attention-based models are conducted with varying sequence lengths from 2K to 4096K. LASP scales sequence length up to 4096K on 128 GPUs, which is 8$\times$ longer than existing SP methods. Code is available at: \url{https://github.com/OpenNLPLab/LASP}.

PDF Details

NeurIPS Conference 2025 Conference Paper

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

  • Yidi Liu
  • Xueyang Fu
  • Jie Huang
  • Jie Xiao
  • Dong Li
  • Wenlong Zhang
  • Lei Bai
  • Zheng-Jun Zha

Ultra-High Definition (UHD) image restoration struggles to balance computational efficiency and detail retention. While Variational Autoencoders (VAEs) offer improved efficiency by operating in the latent space, with the Gaussian variational constraint, this compression preserves semantics but sacrifices critical high-frequency attributes specific to degradation and thus compromises reconstruction fidelity. % This compromises reconstruction fidelity, even when global semantics are preserved. Consequently, a VAE redesign is imperative to foster a robust semantic representation conducive to generalization and perceptual quality, while simultaneously enabling effective high-frequency information processing crucial for reconstruction fidelity. To address this, we propose \textit{Latent Harmony}, a two-stage framework that reinvigorates VAEs for UHD restoration by concurrently regularizing the latent space and enforcing high-frequency-aware reconstruction constraints. Specifically, Stage One introduces the LH-VAE, which fortifies its latent representation through visual semantic constraints and progressive degradation perturbation for enhanced semantics robustness; meanwhile, it incorporates latent equivariance to bolster its high-frequency reconstruction capabilities. Then, Stage Two facilitates joint training of this refined VAE with a dedicated restoration model. This stage integrates High-Frequency Low-Rank Adaptation (HF-LoRA), featuring two distinct modules: an encoder LoRA, guided by a fidelity-oriented high-frequency alignment loss, tailored for the precise extraction of authentic details from degradation-sensitive high-frequency components; and a decoder LoRA, driven by a perception-oriented loss, designed to synthesize perceptually superior textures. These LoRA modules are meticulously trained via alternating optimization with selective gradient propagation to preserve the integrity of the pre-trained latent structure. This methodology culminates in a flexible fidelity-perception trade-off at inference, managed by an adjustable parameter $\alpha$. Extensive experiments demonstrate that \textit{Latent Harmony} effectively balances perceptual and reconstructive objectives with efficiency, achieving superior restoration performance across diverse UHD and standard-resolution scenarios.

PDF Details

IJCAI Conference 2025 Conference Paper

Learnable Frequency Decomposition for Image Forgery Detection and Localization

  • Dong Li
  • Jiayíng Zhu
  • Yidi Liu
  • Xin Lu
  • Xueyang Fu
  • Jiawei Liu
  • Aiping Liu
  • Zheng-Jun Zha

Concern for image authenticity spurs research in image forgery detection and localization (IFDL). Most deep learning-based methods focus primarily on spatial domain modeling and have not fully explored frequency domain strategies. In this paper, we observe and analyze the frequency characteristic changes caused by image tampering. Observations indicate that manipulation traces are especially prominent in phase components and span both low and high-frequency bands. Based on these findings, we propose a forensic frequency decomposition network (F2D-Net), which incorporates deep Fourier transforms and leverages both phase information and high and low-frequency components to enhance IFDL. Specifically, F2D-Net consists of the Spectral Decomposition Subnetwork (SDSN) and the Frequency Separation Subnetwork (FSSN). The former decomposes the image into amplitude and phase, focusing on learning the semantic content in the phase spectrum to identify forged objects, thus improving forgery detection accuracy. The latter further adaptively decomposes the output of the SDSN to obtain corresponding high and low frequencies, and applies a divide-and-conquer strategy to refine each frequency band, mitigating the optimization difficulties caused by coupled forgery traces across different frequencies, thereby better capturing the pixels belonging to the forged object to improve localization accuracy. Experiments on multiple datasets demonstrate that our method outperforms state-of-the-art image forgery detection and localization techniques both qualitatively and quantitatively.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

  • Pucheng Dang
  • Di Huang
  • Dong Li
  • Kang Chen
  • Yuanbo Wen
  • Qi Guo
  • Xing Hu

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 72. 59\% ($\uparrow 50. 74\%$) for migration tasks.

PDF Details

TMLR Journal 2025 Journal Article

Multi-Modal Foundation Models for Computational Pathology: A Survey

  • Dong Li
  • Guihong Wan
  • Xintao Wu
  • Xinyu Wu
  • Xiaohui Chen
  • Yi He
  • Zhong Chen
  • Peter K Sorger

Foundation models have emerged as a powerful paradigm in computational pathology (CPath), enabling scalable and generalizable analysis of histopathological images. While early developments centered on uni-modal models trained solely on visual data, recent advances have highlighted the promise of multi-modal foundation models that integrate heterogeneous data sources such as textual reports, structured domain knowledge, and molecular profiles. In this survey, we provide a comprehensive and up-to-date review of multi-modal foundation models in CPath, with a particular focus on models built upon hematoxylin and eosin (H&E) stained whole slide images (WSIs) and tile-level representations. We categorize 34 state-of-the-art multi-modal foundation models into three major paradigms: vision-language, vision-knowledge graph, and vision-gene expression. We further divide vision-language models into non-LLM-based and LLM-based approaches. Additionally, we analyze 30 available multi-modal datasets tailored for pathology, grouped into image-text pairs, instruction datasets, and image-other modality pairs. Our survey also presents a taxonomy of downstream tasks, highlights training and evaluation strategies, and identifies key challenges and future directions. We aim for this survey to serve as a valuable resource for researchers and practitioners working at the intersection of pathology and AI.

PDF Details

IJCAI Conference 2025 Conference Paper

PanComplex: Leveraging Complex-Valued Neural Networks for Enhanced Pansharpening

  • Chunhui Luo
  • Dong Li
  • Xiaoliang Ma
  • Xin Lu
  • Zhiyuan Wang
  • Jiangtong Tan
  • Xueyang Fu

Pansharpening combines panchromatic and low-resolution multispectral images to generate high-resolution multispectral images. Previous studies have explored the connection between pansharpening and the frequency domain, but mostly in the real-valued domain, leaving the complex domain relatively unexplored. To redefine the pansharpening task, we propose a complex-valued spatial-frequency dual-domain framework, PanComplex. To achieve this, we first establish complex representations and introduce basic complex operators tailored to pansharpening, enabling the transformation of multispectral real-valued signals into the complex domain for learning. We then model both spatial and frequency branches to capture global frequency features and local spatial features comprehensively. Finally, we employ a complex-based interaction module to fuse the spatial and frequency features, achieving complementary information across both domains. By using the representation power of the complex domain, PanComplex effectively extracts complementary features from PAN and MS images, thereby enhancing pansharpening performance. Experiments on multiple datasets demonstrate that our method achieves optimal performance with the fewest parameters and exhibits strong generalization ability to other tasks. The source code for this work is publicly available at https: //github. com/lch-ustc/PanComplex.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Reinforced In-Context Black-Box Optimization

  • Lei Song
  • Chen-Xiao Gao
  • Ke Xue
  • Chenyang Wu
  • Dong Li
  • Jianye Hao
  • Zongzhang Zhang
  • Chao Qian

Black-Box Optimization (BBO) has found successful applications in many fields of science and engineering. Recently, there has been a growing interest in meta-learning particular components of BBO algorithms to speed up optimization and get rid of tedious hand-crafted heuristics. As an extension, learning the entire algorithm from data requires the least labor from experts and can provide the most flexibility. In this paper, we propose RIBBO, a method to reinforce-learn a BBO algorithm from offline data in an end-to-end fashion. RIBBO employs expressive sequence models to learn the optimization histories produced by multiple behavior algorithms and tasks, leveraging the in-context learning ability of large models to extract task information and make decisions accordingly. Central to our method is to augment the optimization histories with regret-to-go tokens, which are designed to represent the performance of an algorithm based on cumulative regret over the future part of the histories. The integration of regret-to-go tokens enables RIBBO to automatically generate sequences of query points that are positively correlated to the user-desired regret, verified by its universally good empirical performance on diverse problems, including BBO benchmark, hyper-parameter optimization, and robot control problems.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

  • Dong Li
  • Xujiang Zhao
  • Linlin Yu
  • Yanchi Liu
  • Wei Cheng
  • Zhengzhang Chen
  • Zhong Chen
  • Feng Chen

Large Language Models (LLMs) offer promising capabilities for tackling complex reasoning tasks, including optimization problems. However, existing methods either rely on prompt engineering, which leads to poor generalization across problem types, or require costly supervised training. We introduce SolverLLM, a training-free framework that leverages test-time scaling to solve diverse optimization problems. Rather than solving directly, SolverLLM generates mathematical formulations and translates them into solver-ready code, guided by a novel Monte Carlo Tree Search (MCTS) strategy. To enhance the search process, we modify classical MCTS with (1) dynamic expansion for adaptive formulation generation, (2) prompt backpropagation to guide exploration via outcome-driven feedback, and (3) uncertainty backpropagation to incorporate reward reliability into decision-making. Experiments on six standard benchmark datasets demonstrate that SolverLLM outperforms both prompt-based and learning-based baselines, achieving strong generalization without additional training.

PDF Details

IROS Conference 2025 Conference Paper

STG-Avatar: Animatable Human Avatars via Spacetime Gaussian

  • Guangan Jiang
  • Tianzi Zhang
  • Dong Li
  • Zhenjun Zhao
  • Haoang Li
  • Mingrui Li
  • Hongyu Wang 0001

Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DGS-based human avatars has made progress, it still struggles with accurately representing detailed features of non-rigid objects (e. g. , clothing deformations) and dynamic regions (e. g. , rapidly moving limbs). To address these challenges, we present STG-Avatar, a 3DGS-based framework for high-fidelity animatable human avatar reconstruction. Specifically, our framework introduces a rigid-nonrigid coupled deformation framework that synergistically integrates Spacetime Gaussians (STG) with linear blend skinning (LBS). In this hybrid design, LBS enables real-time skeletal control by driving global pose transformations, while STG complements it through spacetime-adaptive optimization of 3D Gaussians. Furthermore, we employ optical flow to identify high-dynamic regions and guide the adaptive densification of 3D Gaussians in these regions. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines in both reconstruction quality and operational efficiency, achieving superior quantitative metrics while retaining real-time rendering capabilities. Our code is available at https://github.com/jiangguangan/STG-Avatar

Details

IROS Conference 2025 Conference Paper

TWC-SLAM: Multi-Agent Cooperative SLAM with Text Semantics and WiFi Features Integration for Similar Indoor Environments

  • Chunyu Li
  • Shoubin Chen
  • Dong Li
  • Weixing Xue
  • Qingquan Li 0001

Multi-agent cooperative SLAM often encounters challenges in similar indoor environments characterized by repetitive structures, such as corridors and rooms. These challenges can lead to significant inaccuracies in shared location identification when employing point cloud-based techniques. To mitigate these issues, we introduce TWC-SLAM, a multi-agent cooperative SLAM framework that integrates text semantics and WiFi signal features to enhance location identification and loop closure detection. TWC-SLAM comprises a single-agent front-end odometry module based on FAST-LIO2, a location identification and loop closure detection module that leverages text semantics and WiFi features, and a global mapping module. The agents are equipped with sensors capable of capturing textual information and detecting WiFi signals. By correlating these data sources, TWC-SLAM establishes a common location, facilitating point cloud alignment across different agents’ maps. Furthermore, the system employs loop closure detection and optimization modules to achieve global optimization and cohesive mapping. We evaluated our approach using an indoor dataset featuring similar corridors, rooms, and text sign. The results demonstrate that TWC-SLAM significantly improves the performance of cooperative SLAM systems in complex environments with repetitive architectural features.

Details

NeurIPS Conference 2025 Conference Paper

Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization

  • Guanchen Li
  • Yixing Xu
  • Zeping Li
  • Ji Liu
  • Xuanwu Yin
  • Dong Li
  • Emad Barsoum

Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) yet often fails to maintain comparable performance. Local pruning performs efficient layer-by-layer compression but ignores global topology. Although global pruning aims to identify an optimal sparse model, intuitive methods typically adopt a two-stage paradigm that first evaluates substructure saliency and then applies global pruning, which ignores inter-structure dependencies and fails to achieve end-to-end optimization. To address these limitations, we propose Týr-the-Pruner, an efficient end-to-end search-based global structural pruning framework. This framework constructs a supernet by repeatedly applying local pruning across a range of sparsity ratios to each layer in an LLM, with the core goal of determining the optimal sparsity distribution under a target overall sparsity ratio. Concretely, we introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction. Furthermore, we employ an iterative prune-and-search strategy with coarse-to-fine sparsity granularity to ensure efficient search convergence. Experimental results show that Týr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance while removing a challenging 50% of Llama-3. 1-70B's parameters.

PDF Details

NeurIPS Conference 2024 Conference Paper

An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning

  • Dong Li
  • Aijia Zhang
  • Junqi Gao
  • Biqing Qi

Graph incremental learning has gained widespread attention for its ability to mitigate catastrophic forgetting for graph neural networks (GNN). Conventional methods typically require numerous labels for node classification. However, obtaining abundant labels is often challenging in practice, which makes graph few-shot incremental learning necessary. Current approaches rely on large number of samples from meta-learning to construct memories, and heavy fine-tuning of the GNN parameters that lead to the loss of past knowledge. These result in significant memory consumption and loss of past knowledge information, respectively. To tackle these issues, We introduce Mecoin to efficient construct and Preserve memory. For efficient storage and update of class prototypes, Mecoin use Structured Memory Unit (SMU) to cache prototypes of the seen classes and update new class prototypes through interaction between nodes and the cached prototypes by Memory Construction module(MeCo). Besides, to avoid extensive parameter fine-tuning and forgetting, we introduce a Memory Representation Adaptive Module called MRaM to separate the learning of prototypes and class representations and use Graph Knowledge Interchange Module (GKIM) to injects past knowledge information into GNN. We analyze the effectiveness of our paradigm from the perspectives of generalization error, and discuss the impact of different distillation methods on model performance through experiments and VC-dimension. By comparison with other related methods, we validate that Mecoin achieves higher accuracy and lower forgetting rate.

PDF Details DOI

AAAI Conference 2024 Conference Paper

CatmullRom Splines-Based Regression for Image Forgery Localization

  • Li Zhang
  • Mingliang Xu
  • Dong Li
  • Jianming Du
  • Rujing Wang

IFL (Image Forgery Location) helps secure digital media forensics. However, many methods suffer from false detections (i.e., FPs) and inaccurate boundaries. In this paper, we proposed the CatmullRom Splines-based Regression Network (CSR-Net), which first rethinks the IFL task from the perspective of regression to deal with this problem. Specifically speaking, we propose an adaptive CutmullRom splines fitting scheme for coarse localization of the tampered regions. Then, for false positive cases, we first develop a novel re-scoring mechanism, which aims to filter out samples that cannot have responses on both the classification branch and the instance branch. Later on, to further restrict the boundaries, we design a learnable texture extraction module, which refines and enhances the contour representation by decoupling the horizontal and vertical forgery features to extract a more robust contour representation, thus suppressing FPs. Compared to segmentation-based methods, our method is simple but effective due to the unnecessity of post-processing. Extensive experiments show the superiority of CSR-Net to existing state-of-the-art methods, not only on standard natural image datasets but also on social media datasets.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization

  • Haowei Zhu
  • Dehua Tang
  • Ji Liu
  • Mingjie Lu
  • Jintu Zheng
  • Jinzhang Peng
  • Dong Li
  • Yu Wang

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. While traditional pruning methods have been employed to optimize these models, the retraining process necessitates large-scale training datasets and extensive computational costs to maintain generalization ability, making it neither convenient nor efficient. Recent studies attempt to utilize the similarity of features across adjacent denoising stages to reduce computational costs through simple and static strategies. However, these strategies cannot fully harness the potential of the similar feature patterns across adjacent timesteps. In this work, we propose a novel pruning method that derives an efficient diffusion model via a more intelligent and differentiable pruner. At the core of our approach is casting the model pruning process into a SubNet search process. Specifically, we first introduce a SuperNet based on standard diffusion via adding some backup connections built upon the similar features. We then construct a plugin pruner network and design optimization losses to identify redundant computation. Finally, our method can identify an optimal SubNet through few-step gradient optimization and a simple post-processing procedure. We conduct extensive experiments on various diffusion models including Stable Diffusion series and DiTs. Our DiP-GO approach achieves 4. 4 x speedup for SD-1. 5 without any loss of accuracy, significantly outperforming the previous state-of-the-art methods.

PDF Details DOI

AAAI Conference 2024 Conference Paper

DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems

  • Bowen Wang
  • Chen Liang
  • Jiaze Wang
  • Jiezhong Qiu
  • Furui Liu
  • Shaogang Hao
  • Dong Li
  • Guangyong Chen

Attaining the equilibrium geometry of a catalyst-adsorbate system is key to fundamentally assessing its effective properties, such as adsorption energy. While machine learning methods with advanced representation or supervision strategies have been applied to boost and guide the relaxation processes of catalysis systems, existing methods that produce linearly aggregated geometry predictions are susceptible to edge representations ambiguity, and are therefore vulnerable to graph variations. In this paper, we present a novel graph neural network (GNN) supervision and prediction strategy DR-Label. Our approach mitigates the multiplicity of solutions in edge representation and encourages model predictions that are independent of graph structural variations. DR-Label first Deconstructs finer-grained equilibrium state information to the model by projecting the node-level supervision signal to each edge. Reversely, the model Reconstructs a more robust equilibrium state prediction by converting edge-level predictions to node-level via a sphere-fitting algorithm. When applied to three fundamentally different models, DR-Label consistently enhanced performance. Leveraging the graph structure invariance of the DR-Label strategy, we further propose DRFormer, which applied explicit intermediate positional update and achieves a new state-of-the-art performance on the Open Catalyst 2020 (OC20) dataset and the Cu-based single-atom alloys CO adsorption (SAA) dataset. We expect our work to highlight vital principles for advancing geometric GNN models for catalysis systems and beyond. Our code is available at https://github.com/bowenwang77/DR-Label

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

FinBen: A Holistic Financial Benchmark for Large Language Models

  • Qianqian Xie
  • Weiguang Han
  • Zhengyu Chen
  • Ruoyu Xiang
  • Xiao Zhang
  • Yueru He
  • Mengxi Xiao
  • Dong Li

LLMs have transformed NLP and shown promise in various fields, yet their potential in finance is underexplored due to a lack of comprehensive benchmarks, the rapid development of LLMs, and the complexity of financial tasks. In this paper, we introduce FinBen, the first extensive open-source evaluation benchmark, including 42 datasets spanning 24 financial tasks, covering eight critical aspects: information extraction (IE), textual analysis, question answering (QA), text generation, risk management, forecasting, decision-making, and bilingual (English and Spanish). FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and two novel datasets for regulations and stock trading. Our evaluation of 21 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting. GPT-4 excels in IE and stock trading, while Gemini is better at text generation and forecasting. Instruction-tuned LLMs improve textual analysis but offer limited benefits for complex tasks such as QA. FinBen has been used to host the first financial LLMs shared task at the FinNLP-AgentScen workshop during IJCAI-2024, attracting 12 teams. Their novel solutions outperformed GPT-4, showcasing FinBen's potential to drive innovations in financial LLMs. All datasets and code are publicly available for the research community, with results shared and updated regularly on the Open Financial LLM Leaderboard.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

  • Yangyang Yu
  • Zhiyuan Yao
  • Haohang Li
  • Zhiyang Deng
  • Yuechen Jiang
  • Yupeng Cao
  • Zhi Chen
  • Jordan W. Suchow

Large language models (LLMs) have demonstrated notable potential in conducting complex tasks and are increasingly utilized in various financial applications. However, high-quality sequential financial investment decision-making remains challenging. These tasks require multiple interactions with a volatile environment for every decision, demanding sufficient intelligence to maximize returns and manage risks. Although LLMs have been used to develop agent systems that surpass human teams and yield impressive investment returns, opportunities to enhance multi-source information synthesis and optimize decision-making outcomes through timely experience refinement remain unexplored. Here, we introduce FinCon, an LLM-based multi-agent framework tailored for diverse financial tasks. Inspired by effective real-world investment firm organizational structures, FinCon utilizes a manager-analyst communication hierarchy. This structure allows for synchronized cross-functional agent collaboration towards unified goals through natural language interactions and equips each agent with greater memory capacity than humans. Additionally, a risk-control component in FinCon enhances decision quality by episodically initiating a self-critiquing mechanism to update systematic investment beliefs. The conceptualized beliefs serve as verbal reinforcement for the future agent’s behavior and can be selectively propagated to the appropriate node that requires knowledge updates. This feature significantly improves performance while reducing unnecessary peer-to-peer communication costs. Moreover, FinCon demonstrates strong generalization capabilities in various financial tasks, including stock trading and portfolio management.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

iVideoGPT: Interactive VideoGPTs are Scalable World Models

  • Jialong Wu
  • Shaofeng Yin
  • Ningya Feng
  • Xu He
  • Dong Li
  • Jianye Hao
  • Mingsheng Long

World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals—visual observations, actions, and rewards—into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations. Leveraging its scalable architecture, we are able to pre-train iVideoGPT on millions of human and robotic manipulation trajectories, establishing a versatile foundation that is adaptable to serve as interactive world models for a wide range of downstream tasks. These include action-conditioned video prediction, visual planning, and model-based reinforcement learning, where iVideoGPT achieves competitive performance compared with state-of-the-art methods. Our work advances the development of interactive general world models, bridging the gap between generative video models and practical model-based reinforcement learning applications. Code and pre-trained models are available at https: //thuml. github. io/iVideoGPT.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Learning Discriminative Noise Guidance for Image Forgery Detection and Localization

  • Jiaying Zhu
  • Dong Li
  • Xueyang Fu
  • Gang Yang
  • Jie Huang
  • Aiping Liu
  • Zheng-Jun Zha

This study introduces a new method for detecting and localizing image forgery by focusing on manipulation traces within the noise domain. We posit that nearly invisible noise in RGB images carries tampering traces, useful for distinguishing and locating forgeries. However, the advancement of tampering technology complicates the direct application of noise for forgery detection, as the noise inconsistency between forged and authentic regions is not fully exploited. To tackle this, we develop a two-step discriminative noise-guided approach to explicitly enhance the representation and use of noise inconsistencies, thereby fully exploiting noise information to improve the accuracy and robustness of forgery detection. Specifically, we first enhance the noise discriminability of forged regions compared to authentic ones using a de-noising network and a statistics-based constraint. Then, we merge a model-driven guided filtering mechanism with a data-driven attention mechanism to create a learnable and differentiable noise-guided filter. This sophisticated filter allows us to maintain the edges of forged regions learned from the noise. Comprehensive experiments on multiple datasets demonstrate that our method can reliably detect and localize forgeries, surpassing existing state-of-the-art methods.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Migraine versus tension-type headache in automatic emotional processing: A visual mismatch negativity study

  • Yunliang Guo
  • Shuo Zhao
  • Xunyao Hou
  • Song Xu
  • Shanjing Nie
  • Dong Li
  • Ximing Wang
  • Chuanchen Zhang

OBJECTIVE: It is important to discriminate different headaches in clinical practice, and neurocognitive biomarkers may serve as objective tools. Several reports have suggested potential cognitive impairment for primary headaches, whereas cognitions within specific domains remain elusive, e.g., emotional processing. In this study, we aimed to characterize processing of facial expressions in migraine and tension-type headache (TTH) by analyzing expression-related visual mismatch negativity (EMMN) and explored whether their processing patterns were distinct. METHODS: Altogether, 73 headache patients (20 migraine with aura (MA), 28 migraine without aura (MwoA), 25 TTH) and 27 age-matched healthy controls were recruited. After a battery of mood/neuropsychological evaluations, an expression-related oddball paradigm containing multiple models of neutral, happy and sad faces was used to investigate automatic emotional processing. RESULTS: We observed cognitive impairment in all headache patients, especially in attention/execution subdomains, but no discrepancy existed among different headaches. Although analyses of P1/N170 did not reach significant levels, amplitude of early and late EMMN was markedly diminished in MA and MwoA compared with controls and TTH, regardless of happy or sad expression. Moreover, sad EMMN was larger (more negative) than happy EMMN only in controls, while not in all headache groups. CONCLUSIONS: Our findings implied that migraine, rather than TTH, might lead to more severe impairment of automatic emotional processing, which was manifested as no observable EMMN elicitation and disappearance of negative bias effect. The EMMN component could assist in discrimination of migraine from TTH and diagnosis of undefined headaches, and its availability needed further validations.

Details DOI

AAAI Conference 2024 Conference Paper

Multiagent Gumbel MuZero: Efficient Planning in Combinatorial Action Spaces

  • Xiaotian Hao
  • Jianye Hao
  • Chenjun Xiao
  • Kai Li
  • Dong Li
  • Yan Zheng

AlphaZero and MuZero have achieved state-of-the-art (SOTA) performance in a wide range of domains, including board games and robotics, with discrete and continuous action spaces. However, to obtain an improved policy, they often require an excessively large number of simulations, especially for domains with large action spaces. As the simulation budget decreases, their performance drops significantly. In addition, many important real-world applications have combinatorial (or exponential) action spaces, making it infeasible to search directly over all possible actions. In this paper, we extend AlphaZero and MuZero to learn and plan in more complex multiagent (MA) Markov decision processes, where the action spaces increase exponentially with the number of agents. Our new algorithms, MA Gumbel AlphaZero and MA Gumbel MuZero, respectively without and with model learning, achieve superior performance on cooperative multiagent control problems, while reducing the number of environmental interactions by up to an order of magnitude compared to model-free approaches. In particular, we significantly improve prior performance when planning with much fewer simulation budgets. The code and appendix are available at https://github.com/tjuHaoXiaotian/MA-MuZero.

PDF Details DOI

AAAI Conference 2024 Conference Paper

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

  • Taicai Chen
  • Yue Duan
  • Dong Li
  • Lei Qi
  • Yinghuan Shi
  • Yang Gao

Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, current mainstream methods overlook the potential of utilizing a pool of unlabeled data to construct the latent space, while only concentrating on designing sophisticated models to leverage the labeled data. Despite their effective usage of labeled data, these methods often require extra network structures, additional procedure, resulting in computational inefficiency. To address this issue, we propose a novel method to effectively utilize unlabeled data with the guidance of labeled data. Specifically, we tailor the pseudo-labeling technique from semi-supervised learning to explicitly reveal the relative magnitudes of optimization objective values hidden within the unlabeled data. Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space. Furthermore, we treat the VAE encoder and the Gaussian Process (GP) in Bayesian optimization as a unified deep kernel learning process, allowing the direct utilization of labeled data, which we term as Gaussian Process guidance. This directly and effectively integrates the goal of improving GP accuracy into the VAE training, thereby guiding the construction of the latent space. The extensive experiments demonstrate that our proposed method outperforms existing VAE-BO algorithms in various optimization scenarios. Our code will be published at https://github.com/TaicaiChen/PG-LBO.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion

  • Yixing Xu
  • Chao Li
  • Dong Li
  • Xiao Sheng
  • Fan Jiang
  • Lu Tian
  • Emad Barsoum

Vision transformer model (ViT) is widely used and performs well in vision tasks due to its ability to capture long-range dependencies. However, the time complexity and memory consumption increase quadratically with the number of input patches which limits the usage of ViT in real-world applications. Previous methods have employed linear attention to mitigate the complexity of the original self-attention mechanism at the expense of effectiveness. In this paper, we propose QT-ViT models that improve the previous linear self-attention using quadratic Taylor expansion. Specifically, we substitute the softmax-based attention with second-order Taylor expansion, and then accelerate the quadratic expansion by reducing the time complexity with a fast approximation algorithm. The proposed method capitalizes on the property of quadratic expansion to achieve superior performance while employing linear approximation for fast inference. Compared to previous studies of linear attention, our approach does not necessitate knowledge distillation or high-order attention residuals to facilitate the training process. Extensive experiments demonstrate the efficiency and effectiveness of the proposed QT-ViTs, showcasing the state-of-the-art results. Particularly, the proposed QT-ViTs consistently surpass the previous SOTA EfficientViTs under different model sizes, and achieve a new Pareto-front in terms of accuracy and speed.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Supervised Algorithmic Fairness in Distribution Shifts: A Survey

  • Minglai Shao
  • Dong Li
  • Chen Zhao
  • Xintao Wu
  • Yujie Lin
  • Qin Tian

Supervised fairness-aware machine learning under distribution shifts is an emerging field that addresses the challenge of maintaining equitable and unbiased predictions when faced with changes in data distributions from source to target domains. In real-world applications, machine learning models are often trained on a specific dataset but deployed in environments where the data distribution may shift over time due to various factors. This shift can lead to unfair predictions, disproportionately affecting certain groups characterized by sensitive attributes, such as race and gender. In this survey, we provide a summary of various types of distribution shifts and comprehensively investigate existing methods based on these shifts, highlighting six commonly used approaches in the literature. Additionally, this survey lists publicly available datasets and evaluation metrics for empirical studies. We further explore the interconnection with related research fields, discuss the significant challenges, and identify potential directions for future studies.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy

  • Chengrui Gao
  • Haopu Shang
  • Ke Xue
  • Dong Li
  • Chao Qian

Machine learning has been adapted to help solve NP-hard combinatorial optimization problems. One prevalent way is learning to construct solutions by deep neural networks, which has been receiving more and more attention due to the high efficiency and less requirement for expert knowledge. However, many neural construction methods for Vehicle Routing Problems~(VRPs) focus on synthetic problem instances with specified node distributions and limited scales, leading to poor performance on real-world problems which usually involve complex and unknown node distributions together with large scales. To make neural VRP solvers more practical, we design an auxiliary policy that learns from the local transferable topological features, named local policy, and integrate it with a typical construction policy (which learns from the global information of VRP instances) to form an ensemble policy. With joint training, the aggregated policies perform cooperatively and complementarily to boost generalization. The experimental results on two well-known benchmarks, TSPLIB and CVRPLIB, of travelling salesman problem and capacitated VRP show that the ensemble policy significantly improves both cross-distribution and cross-scale generalization performance, and even performs well on real-world problems with several thousand nodes.

PDF Details DOI

IROS Conference 2024 Conference Paper

UMAD: University of Macau Anomaly Detection Benchmark Dataset

  • Dong Li
  • Lineng Chen
  • ChengZhong Xu 0001
  • Hui Kong 0001

Anomaly detection is critical in surveillance systems and patrol robots by identifying anomalous regions in images for early warning. Depending on whether reference data are utilized, anomaly detection can be categorized into anomaly detection with reference and anomaly detection without reference. Currently, anomaly detection without reference, which is closely related to out-of-distribution (OoD) object detection, struggles with learning anomalous patterns due to the difficulty of collecting sufficiently large and diverse anomaly datasets with the inherent rarity and novelty of anomalies. Alternatively, anomaly detection with reference employs the scheme of change detection to identify anomalies by comparing semantic changes between a reference image and a query one. However, there are very few ADr works due to the scarcity of public datasets in this domain. In this paper, we aim to address this gap by introducing the UMAD Benchmark Dataset. To our best knowledge, this is the first benchmark dataset designed specifically for anomaly detection with reference in robotic patrolling scenarios, e. g. , where an autonomous robot is employed to detect anomalous objects by comparing a reference and a query video sequences. The reference sequences can be taken by the robot along a specified route when there are no anomalous objects in the scene. The query sequences are captured online by the robot when it is patrolling in the same scene following the same route. Our benchmark dataset is elaborated such that each query image can find a corresponding reference based on accurate robot localization along the same route in the pre-built 3D map, with which the reference and query images can be geometrically aligned using adaptive warping. Besides the proposed benchmark dataset, we evaluate the baseline models of ADr on this dataset. We hope this benchmark dataset will facilitate the advancement of ADr methods in the future. Our UMAD benchmark dataset will be publicly accessible at https://github.com/IMRL/UMAD.

Details

AAAI Conference 2024 Conference Paper

UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer

  • Ji Liu
  • Dehua Tang
  • Yuanxian Huang
  • Li Zhang
  • Xiaocheng Zeng
  • Dong Li
  • Mingjie Lu
  • Jinzhang Peng

Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet with directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel depth pruning method for efficient models. Our approach proposes a novel block pruning strategy and progressive training method for the subnet. Additionally, we extend our pruning method to vision transformer models. Experimental results demonstrate that our method consistently outperforms existing depth pruning methods across various pruning configurations. We obtained three pruned ConvNeXtV1 models with our method applying on ConvNeXtV1, which surpass most SOTA efficient models with comparable inference performance. Our method also achieves state-of-the-art pruning performance on the vision transformer model.

PDF Details DOI

EAAI Journal 2023 Journal Article

Continual learning classification method with human-in-the-loop based on the artificial immune system

  • Jia Liu
  • Dong Li
  • Wangweiyi Shan
  • Shulin Liu

Currently, most classification algorithms may suffer from serious misclassification when faced with unbalanced or new data, for lacking feedback and update capability. Many existing classification methods learn from the continuous learning mechanism in the biological immune system to realize the learning of new data. However, these methods in classifying new data, because of the lack of feedback, lead to a search for a long time, even may deviate from the correct results. Humans can make the immune response proceed to a certain extent as they wish through a variety of intervention techniques. Motivated by this, this paper proposes a continual learning classification method with human-in-the-loop (H-CLCM) based on the artificial immune system. H-CLCM adjusts parameters online corresponding to misidentified data by integrating human experience during the testing phase. This enables it not only to converge to an accurate prediction model at minimal cost but also to have the capability to learn new classes of data without retraining the classifier. Experiments on 10 benchmark datasets demonstrate the performances and advantages of the proposed method. The experimental results show that H-CLCM has superior classification performance than the other approaches under the same data.

Details DOI

JBHI Journal 2023 Journal Article

Convolutional Feature Descriptor Selection for Mammogram Classification

  • Dong Li
  • Lei Zhang
  • Jianwei Zhang
  • Xingyu Xie

Breast cancer was the most commonly diagnosed cancer among women worldwide in 2020. Recently, several deep learning-based classification approaches have been proposed to screen breast cancer in mammograms. However, most of these approaches require additional detection or segmentation annotations. Meanwhile, some other image-level label-based methods often pay insufficient attention to lesion areas, which are critical for diagnosis. This study designs a novel deep-learning method for automatically diagnosing breast cancer in mammography, which focuses on the local lesion areas and only utilizes image-level classification labels. In this study, we propose to select discriminative feature descriptors from feature maps instead of identifying lesion areas using precise annotations. And we design a novel adaptive convolutional feature descriptor selection (AFDS) structure based on the distribution of the deep activation map. Specifically, we adopt the triangle threshold strategy to calculate a specific threshold for guiding the activation map to determine which feature descriptors (local areas) are discriminative. Ablation experiments and visualization analysis indicate that the AFDS structure makes the model easier to learn the difference between malignant and benign/normal lesions. Furthermore, since the AFDS structure can be regarded as a highly efficient pooling structure, it can be easily plugged into most existing convolutional neural networks with negligible effort and time consumption. Experimental results on two publicly available INbreast and CBIS-DDSM datasets indicate that the proposed method performs satisfactorily compared with state-of-the-art methods.

Details DOI

TMLR Journal 2023 Journal Article

Differentiable Logic Machines

  • Matthieu Zimmer
  • Xuening Feng
  • Claire Glanois
  • Zhaohui Jiang
  • Jianyi Zhang
  • Paul Weng
  • Dong Li
  • Jianye Hao

The integration of reasoning, learning, and decision-making is key to build more general artificial intelligence systems. As a step in this direction, we propose a novel neural-logic architecture, called differentiable logic machine (DLM), that can solve both inductive logic programming (ILP) and reinforcement learning (RL) problems, where the solution can be interpreted as a first-order logic program. Our proposition includes several innovations. Firstly, our architecture defines a restricted but expressive continuous relaxation of the space of first-order logic programs by assigning weights to predicates instead of rules, in contrast to most previous neural-logic approaches. Secondly, with this differentiable architecture, we propose several (supervised and RL) training procedures, based on gradient descent, which can recover a fully-interpretable solution (i.e., logic formula). Thirdly, to accelerate RL training, we also design a novel critic architecture that enables actor-critic algorithms. Fourthly, to solve hard problems, we propose an incremental training procedure that can learn a logic program progressively. Compared to state-of-the-art (SOTA) differentiable ILP methods, DLM successfully solves all the considered ILP problems with a higher percentage of successful seeds (up to 3.5x). On RL problems, without requiring an interpretable solution, DLM outperforms other non-interpretable neural-logic RL approaches in terms of rewards (up to 3.9%). When enforcing interpretability, DLM can solve harder RL problems (e.g., Sorting, Path) than other interpretable RL methods. Moreover, we show that deep logic programs can be learned via incremental supervised training. In addition to this excellent performance, DLM can scale well in terms of memory and computational time, especially during the testing phase where it can deal with much more constants (>2x) than SOTA.

PDF Details

NeurIPS Conference 2023 Conference Paper

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

  • Junqi Gao
  • Biqing Qi
  • Yao Li
  • Zhichang Guo
  • Dong Li
  • Yuming Xing
  • Dazhi Zhang

The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to transfer between models. In this paper, we experimentally and theoretically demonstrated that neural networks trained on the same dataset have more consistent performance in High-Sample-Density-Regions (HSDR) of each class instead of low sample density regions. Therefore, in the target setting, adding perturbations towards HSDR of the target class is more effective in improving transferability. However, density estimation is challenging in high-dimensional scenarios. Further theoretical and experimental verification demonstrates that easy samples with low loss are more likely to be located in HSDR. Perturbations towards such easy samples in the target class can avoid density estimation for HSDR location. Based on the above facts, we verified that adding perturbations to easy samples in the target class improves targeted adversarial transferability of existing attack methods. A generative targeted attack strategy named Easy Sample Matching Attack (ESMA) is proposed, which has a higher success rate for targeted attacks and outperforms the SOTA generative method. Moreover, ESMA requires only $5\%$ of the storage space and much less computation time comparing to the current SOTA, as ESMA attacks all classes with only one model instead of seperate models for each class. Our code is available at https: //github. com/gjq100/ESMA

PDF Details

NeurIPS Conference 2023 Conference Paper

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

  • Yi Ma
  • Hongyao Tang
  • Dong Li
  • Zhaopeng Meng

Offline Reinforcement Learning (RL) aims to address the challenge of distribution shift between the dataset and the learned policy, where the value of out-of-distribution (OOD) data may be erroneously estimated due to overgeneralization. It has been observed that a considerable portion of the benefits derived from the conservative terms designed by existing offline RL approaches originates from their impact on the learned representation. This observation prompts us to scrutinize the learning dynamics of offline RL, formalize the process of generalization, and delve into the prevalent overgeneralization issue in offline RL. We then investigate the potential to rein the generalization from the representation perspective to enhance offline RL. Finally, we present Representation Distinction (RD), an innovative plug-in method for improving offline RL algorithm performance by explicitly differentiating between the representations of in-sample and OOD state-action pairs generated by the learning policy. Considering scenarios in which the learning policy mirrors the behavioral policy and similar samples may be erroneously distinguished, we suggest a dynamic adjustment mechanism for RD based on an OOD data generator to prevent data representation collapse and further enhance policy performance. We demonstrate the efficacy of our approach by applying RD to specially-designed backbone algorithms and widely-used offline RL algorithms. The proposed RD method significantly improves their performance across various continuous control tasks on D4RL datasets, surpassing several state-of-the-art offline RL algorithms.

PDF Details

AAAI Conference 2023 Conference Paper

Towards Reliable Item Sampling for Recommendation Evaluation

  • Dong Li
  • Ruoming Jin
  • Zhenming Liu
  • Bin Ren
  • Jing Gao
  • Zhi Liu

Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are ``inconsistent'' with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation. Existing methods try either mapping the sampling-based metrics to their global counterparts or more generally, learning the empirical rank distribution to estimate the top-K metrics. However, despite existing efforts, there is still a lack of rigorous theoretical understanding of the proposed metric estimators, and the basic item sampling also suffers from the ``blind spot'' issue, i.e., estimation accuracy to recover the top-K metrics when K is small can still be rather substantial. In this paper, we provide an in-depth investigation into these problems and make two innovative contributions. First, we propose a new item-sampling estimator that explicitly optimizes the error with respect to the ground truth, and theoretically highlights its subtle difference against prior work. Second, we propose a new adaptive sampling method that aims to deal with the ``blind spot'' problem and also demonstrate the expectation-maximization (EM) algorithm can be generalized for such a setting. Our experimental results confirm our statistical analysis and the superiority of the proposed works. This study helps lay the theoretical foundation for adopting item sampling metrics for recommendation evaluation and provides strong evidence for making item sampling a powerful and reliable tool for recommendation evaluation.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving

  • Li Wang
  • Dong Li
  • Han Liu
  • Jinzhang Peng
  • Lu Tian
  • Yi Shan

Semantic segmentation is an important task for scene understanding in self-driving cars and robotics, which aims to assign dense labels for all pixels in the image. Existing work typically improves semantic segmentation performance by exploring different network architectures on a target dataset. Little attention has been paid to build a unified system by simultaneously learning from multiple datasets due to the inherent distribution shift across different datasets. In this paper, we propose a simple, flexible, and general method for semantic segmentation, termed Cross-Dataset Collaborative Learning (CDCL). Our goal is to train a unified model for improving the performance in each dataset by leveraging information from all the datasets. Specifically, we first introduce a family of Dataset-Aware Blocks (DAB) as the fundamental computing units of the network, which help capture homogeneous convolutional representations and heterogeneous statistics across different datasets. Second, we present a Dataset Alternation Training (DAT) mechanism to facilitate the collaborative optimization procedure. We conduct extensive evaluations on diverse semantic segmentation datasets for autonomous driving. Experiments demonstrate that our method consistently achieves notable improvements over prior single-dataset and cross-dataset training methods without introducing extra FLOPs. Particularly, with the same architecture of PSPNet (ResNet-18), our method outperforms the single-dataset baseline by 5. 65%, 6. 57%, and 5. 79% mIoU on the validation sets of Cityscapes, BDD100K, CamVid, respectively. We also apply CDCL for point cloud 3D semantic segmentation and achieve improved performance, which further validates the superiority and generality of our method. Code and models will be released.

PDF Details

TCS Journal 2022 Journal Article

Dynamic threshold P systems with delay on synapses for shortest path problems

  • Silu Yang
  • Dong Li
  • Hong Peng
  • Wenjie Zhou
  • Xiaohui Luo
  • Qian Yang
  • Jun Wang
  • Xiaoxiao Song

Dynamic threshold neural P (DTNP) systems are recently developed neural-like membrane computing models. By introducing the delay mechanism on synapses, we propose a variant, called dynamic threshold neural P systems with delay on synapses or termed as DTNP-DS systems. DTNP-DS systems possess three recognizable features: spiking mechanism, dynamic threshold mechanism, and delay mechanism on synapses. Based on the three mechanisms, we develop a novel algorithm based on DTNP-DS systems for solving shortest path problems. In principle, the three mechanisms provide a parallel search way for the shortest path in a given network, and they can effectively control the speed and direction of the search. Simulation results demonstrate that DTNP-DS systems can provide an effective solution for the shortest path problems.

Details DOI

NeurIPS Conference 2022 Conference Paper

Versatile Multi-stage Graph Neural Network for Circuit Representation

  • Shuwen Yang
  • Zhihao Yang
  • Dong Li
  • Yingxueff Zhang
  • Zhanguang Zhang
  • Guojie Song
  • Jianye Hao

Due to the rapid growth in the scale of circuits and the desire for knowledge transfer from old designs to new ones, deep learning technologies have been widely exploited in Electronic Design Automation (EDA) to assist circuit design. In chip design cycles, we might encounter heterogeneous and diverse information sources, including the two most informative ones: the netlist and the design layout. However, handling each information source independently is sub-optimal. In this paper, we propose a novel way to integrate the multiple information sources under a unified heterogeneous graph named Circuit Graph, where topological and geometrical information is well integrated. Then, we propose Circuit GNN to fully utilize the features of vertices, edges as well as heterogeneous information during the message passing process. It is the first attempt to design a versatile circuit representation that is compatible across multiple EDA tasks and stages. Experiments on the two most representative prediction tasks in EDA show that our solution reaches state-of-the-art performance in both logic synthesis and global placement chip design stages. Besides, it achieves a 10x speed-up on congestion prediction compared to the state-of-the-art model.

PDF Details

AAAI Conference 2022 Conference Paper

What about Inputting Policy in Value Function: Policy Representation and Policy-Extended Value Function Approximator

  • Hongyao Tang
  • Zhaopeng Meng
  • Jianye Hao
  • Chen Chen
  • Daniel Graves
  • Dong Li
  • Changmin Yu
  • Hangyu Mao

We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation. Such an extension enables PeVFA to preserve values of multiple policies at the same time and brings an appealing characteristic, i. e. , value generalization among policies. We formally analyze the value generalization under Generalized Policy Iteration (GPI). From theoretical and empirical lens, we show that generalized value estimates offered by PeVFA may have lower initial approximation error to true values of successive policies, which is expected to improve consecutive value approximation during GPI. Based on above clues, we introduce a new form of GPI with PeVFA which leverages the value generalization along policy improvement path. Moreover, we propose a representation learning framework for RL policy, providing several approaches to learn effective policy embeddings from policy network parameters or stateaction pairs. In our experiments, we evaluate the efficacy of value generalization offered by PeVFA and policy representation learning in several OpenAI Gym continuous control tasks. For a representative instance of algorithm implementation, Proximal Policy Optimization (PPO) re-implemented under the paradigm of GPI with PeVFA achieves about 40% performance improvement on its vanilla counterpart in most environments.

PDF Details

NeurIPS Conference 2021 Conference Paper

Adaptive Online Packing-guided Search for POMDPs

  • Chenyang Wu
  • Guoyu Yang
  • Zongzhang Zhang
  • Yang Yu
  • Dong Li
  • Wulong Liu
  • Jianye Hao

The partially observable Markov decision process (POMDP) provides a general framework for modeling an agent's decision process with state uncertainty, and online planning plays a pivotal role in solving it. A belief is a distribution of states representing state uncertainty. Methods for large-scale POMDP problems rely on the same idea of sampling both states and observations. That is, instead of exact belief updating, a collection of sampled states is used to approximate the belief; instead of considering all possible observations, only a set of sampled observations are considered. Inspired by this, we take one step further and propose an online planning algorithm, Adaptive Online Packing-guided Search (AdaOPS), to better approximate beliefs with adaptive particle filter technique and balance estimation bias and variance by fusing similar observation branches. Theoretically, our algorithm is guaranteed to find an $\epsilon$-optimal policy with a high probability given enough planning time under some mild assumptions. We evaluate our algorithm on several tricky POMDP domains, and it outperforms the state-of-the-art in all of them.

PDF Details

NeurIPS Conference 2021 Conference Paper

An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning

  • Tianpei Yang
  • Weixun Wang
  • Hongyao Tang
  • Jianye Hao
  • Zhaopeng Meng
  • Hangyu Mao
  • Dong Li
  • Wulong Liu

Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option module can only collect all agent's local experiences for update due to the partial observability of the environment. While in this setting, each agent's experience may be inconsistent with each other, which may cause the inaccuracy and oscillation of the option-value's estimation. Therefore, we propose a novel option learning algorithm, the successor representation option learning to solve it by decoupling the environment dynamics from rewards and learning the option-value under each agent's preference. MAPTF can be easily combined with existing deep RL and MARL approaches, and experimental results show it significantly boosts the performance of existing methods in both discrete and continuous state spaces.

PDF Details

AAAI Conference 2021 Short Paper

Enhancing Context-Based Meta-Reinforcement Learning Algorithms via An Efficient Task Encoder (Student Abstract)

  • Feng Xu
  • Shengyi Jiang
  • Hao Yin
  • Zongzhang Zhang
  • Yang Yu
  • Ming Li
  • Dong Li
  • Wulong Liu

Meta-Reinforcement Learning (meta-RL) algorithms enable agents to adapt to new tasks from small amounts of exploration, based on the experience of similar tasks. Recent studies have pointed out that a good representation of a task is key to the success of off-policy context-based meta-RL. Inspired by contrastive methods in unsupervised representation learning, we propose a new method to learn the task representation based on the mutual information between transition tuples in a trajectory and the task embedding. We also propose a new estimation for task similarity based on Q-function, which can be used to form a constraint on the distribution of the encoded task variables, making the task encoder encode the task variables more effective on new tasks. Experiments on meta-RL tasks show that the newly proposed method outperforms existing meta-RL algorithms.

PDF Details

JBHI Journal 2021 Journal Article

Heartbeats Classification Using Hybrid Time-Frequency Analysis and Transfer Learning Based on ResNet

  • Yatao Zhang
  • Junyan Li
  • Shoushui Wei
  • Fengyu Zhou
  • Dong Li

The classification of heartbeats is an important method for cardiac arrhythmia analysis. This study proposes a novel heartbeat classification method using hybrid time-frequency analysis and transfer learning based on ResNet-101. The proposed method has the following major advantages over the afore-mentioned methods: it avoids the need for manual features extraction in the traditional machine learning method, and it utilizes 2-D time-frequency diagrams which provide not only frequency and energy information but also preserve the morphological characteristic within the ECG recordings, and it owns enough deep to make better use of performance of CNN. The method deploys a hybrid time-frequency analysis of the Hilbert transform (HT) and the Wigner-Ville distribution (WVD) to transform 1-D ECG recordings into 2-D time-frequency diagrams which were then fed into a transfer learning classifier based on ResNet-101 for two classification tasks (i. e. , 5 heartbeat categories assigned by the ANSI/AAMI standard (i. e. , N, V, S, Q and F) and 14 original beat kinds of the MIT/BIH arrhythmia database). For 5 heartbeat categories classification, the results show the F1-score of N, V, S, Q and F categories are F $_{N}$ 0. 9899, F $_{V}$ 0. 9845, F $_{S}$ 0. 9376, F $_{Q}$ 0. 9968, F $_{F}$ 0. 8889, respectively, and the overall F1-score is 0. 9595 using the combination data balancing. The results show the average values for accuracy, sensitivity, specificity, predictive value and F1-score on test set for 14 beat kinds the MIT-BIH arrhythmia database are 99. 75%, 91. 36%, 99. 85%, 90. 81% and 0. 9016, respectively. Compared with other methods, the proposed method can yield more accurate results.

Details DOI

AAAI Conference 2021 Short Paper

LB-DESPOT: Efficient Online POMDP Planning Considering Lower Bound in Action Selection (Student Abstract)

  • Chenyang Wu
  • Rui Kong
  • Guoyu Yang
  • Xianghan Kong
  • Zongzhang Zhang
  • Yang Yu
  • Dong Li
  • Wulong Liu

Partially observable Markov decision process (POMDP) is an extension to MDP. It handles the state uncertainty by specifying the probability of getting a particular observation given the current state. DESPOT is one of the most popular scalable online planning algorithms for POMDPs, which manages to significantly reduce the size of the decision tree while deriving a near-optimal policy by considering only K scenarios. Nevertheless, there is a gap in action selection criteria between planning and execution in DESPOT. During the planning stage, it keeps choosing the action with the highest upper bound, whereas when the planning ends, the action with the highest lower bound is chosen for execution. Here, we propose LB-DESPOT to alleviate this issue, which utilizes the lower bound in selecting an action branch to expand. Empirically, our method has attained better performance than DESPOT and POMCP, which is another state-of-the-art, on several challenging POMDP benchmark tasks.

PDF Details

AAAI Conference 2021 Conference Paper

On Estimating Recommendation Evaluation Metrics under Sampling

  • Ruoming Jin
  • Dong Li
  • Benjamin Mudrak
  • Jing Gao
  • Zhi Liu

Since the recent study done by Krichene and Rendle on the sampling-based top-k evaluation metric for recommendation, there has been a lot of debates on the validity of using sampling to evaluate recommendation algorithms. Though their work and the recent work done by Li et al. have proposed some basic approaches for mapping the sampling-based metrics to their global counterparts which rank the entire set of items, there is still a lack of understanding and consensus on how sampling should be used for recommendation evaluation. The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision. In this paper, we introduce a new research problem on learning the empirical rank distribution, and a new approach based on the estimated rank distribution, to estimate the top-k metrics. Since this question is closely related to the underlying mechanism of sampling for recommendation, tackling it can help better understand the power of sampling and can help resolve the questions of if and how should we use sampling for evaluating recommendation. We introduce two approaches based on MLE (Maximal Likelihood Estimation) and its weighted variants, and ME (Maximal Entropy) principals to recover the empirical rank distribution, and then utilize them for metrics estimation. The experimental results show the advantages of using the new approaches for evaluating recommendation algorithms based on top-k metrics.

PDF Details

IROS Conference 2021 Conference Paper

ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

  • Jun Yang 0053
  • Yizhou Gao
  • Dong Li
  • Steven L. Waslander

In robotic bin-picking applications, the perception of texture-less, highly reflective parts is a valuable but challenging task. The high glossiness can introduce fake edges in RGB images and inaccurate depth measurements, especially in heavily cluttered bin scenarios. In this paper, we present the ROBI (Reflective Objects in BIns) dataset, a public dataset for 6D object pose estimation and multi-view depth fusion in robotic bin-picking scenarios. The ROBI dataset includes a total of 63 bin-picking scenes captured with two active stereo cameras: a high-cost Ensenso sensor and a low-cost RealSense sensor. For each scene, the monochrome/RGB images and depth maps are captured from sampled view spheres around the scene, and are annotated with accurate 6D poses of visible objects and an associated visibility score. For evaluating the performance of depth fusion, we captured the ground truth depth maps by high-cost Ensenso camera with objects coated in anti-reflective scanning spray. To show the utility of the dataset, we evaluated the representative algorithms of 6D object pose estimation and multi-view depth fusion on the full dataset. Evaluation results demonstrate the difficulty of highly reflective objects, especially in difficult cases due to the degradation of depth data quality, severe occlusions, and cluttered scenes. The ROBI dataset is available online at https://www.trailab.utias.utoronto.ca/robi.

Details

AAAI Conference 2021 Conference Paper

Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning

  • Haotian Fu
  • Hongyao Tang
  • Jianye Hao
  • Chen Chen
  • Xidong Feng
  • Dong Li
  • Wulong Liu

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta- RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed the taskspecific information contained in prior trajectories? 2. How to collect informative trajectories of which the corresponding context reflects the specification of tasks? To this end, we propose a novel Meta-RL framework called CCM (Contrastive learning augmented Context-based Meta-RL). We first focus on the contrastive nature behind different tasks and leverage it to train a compact and sufficient context encoder. Further, we train a separate exploration policy and theoretically derive a new information-gain-based objective which aims to collect informative trajectories in a few steps. Empirically, we evaluate our approaches on common benchmarks as well as several complex sparse-reward environments. The experimental results show that CCM outperforms state-of-the-art algorithms by addressing previously mentioned problems respectively.

PDF Details

NeurIPS Conference 2020 Conference Paper

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

  • Jie Ren
  • Minjia Zhang
  • Dong Li

The state-of-the-art approximate nearest neighbor search (ANNS) algorithms face a fundamental tradeoff between query latency and accuracy, because of small main memory capacity: To store indices in main memory for short query latency, the ANNS algorithms have to limit dataset size or use a quantization scheme which hurts search accuracy. The emergence of heterogeneous memory (HM) brings a solution to significantly increase memory capacity and break the above tradeoff: Using HM, billions of data points can be placed in the main memory on a single machine without using any data compression. However, HM consists of both fast (but small) memory and slow (but large) memory, and using HM inappropriately slows down query significantly. In this work, we present a novel graph-based similarity search algorithm called HM-ANN, which takes both memory and data heterogeneity into consideration and enables billion-scale similarity search on a single node without using compression. On two billion-sized datasets BIGANN and DEEP1B, HM-ANN outperforms state-of-the-art compression-based solutions such as L&C and IMI+OPQ in recall-vs-latency by a large margin, obtaining 46% higher recall under the same search latency. We also extend existing graph-based methods such as HNSW and NSG with two strong baseline implementations on HM. At billion-point scale, HM-ANN is 2X and 5. 8X faster than our HNSWand NSG baselines respectively to reach the same accuracy.

PDF Details

AAAI Conference 2020 Conference Paper

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

  • Hangyu Mao
  • Wulong Liu
  • Jianye Hao
  • Jun Luo
  • Dong Li
  • Zhengchao Zhang
  • Jun Wang
  • Zhen Xiao

Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation. Meanwhile, only cognitive consistency within a neighborhood matters because humans only interact directly with their neighbors. Inspired by these observations, we take the first step to introduce neighborhood cognitive consistency (NCC) into multi-agent reinforcement learning (MARL). Our NCC design is quite general and can be easily combined with existing MARL methods. As examples, we propose neighborhood cognition consistent deep Q-learning and Actor-Critic to facilitate large-scale multi-agent cooperations. Extensive experiments on several challenging tasks (i. e. , packet routing, wifi configuration and Google football player control) justify the superior performance of our methods compared with state-of-the-art MARL approaches.

PDF Details

TCS Journal 2019 Journal Article

On g-extra conditional diagnosability of hierarchical cubic networks

  • Huiqing Liu
  • Shunzhe Zhang
  • Dong Li

Connectivity and diagnosability are important parameters in measuring the fault-tolerance and reliability of interconnection networks. Given a graph G and a non-negative integer g, the g-extra connectivity of G, denoted by κ g ( G ), is the minimum cardinality of a set of vertices of G, if it exists, whose deletion disconnects G, and every remaining component has more than g vertices. The g-extra conditional diagnosability t g ( G ) of a graph G is the maximum value of t such that G is g-extra conditional t-diagnosable. The n-dimensional hierarchical cubic network H C N n was proposed by Ghose and Desai [12] as a hypercube-based topology while preserving its attractive features. For n ≥ 5, we first determine κ g ( H C N n ) for 0 ≤ g ≤ n + 1, then establish t g ( H C N n ) under the PMC model for 0 ≤ g ≤ n + 1, and t g ( H C N n ) under the MM⁎ model for 0 ≤ g ≤ n − 1 3, respectively.

Details DOI

TCS Journal 2019 Journal Article

Structure connectivity and substructure connectivity of twisted hypercubes

  • Dong Li
  • Xiaolan Hu
  • Huiqing Liu

Let G be a graph and T a certain connected subgraph of G. The T-structure connectivity κ ( G; T ) (or resp. , T-substructure connectivity κ s ( G; T ) ) of G is the minimum number of a set of subgraphs F = { T 1, T 2, …, T m } (or resp. , F = { T 1 ′, T 2 ′, …, T m ′ } ) such that T i is isomorphic to T (or resp. , T i ′ is a connected subgraph of T) for every 1 ≤ i ≤ m, and F 's removal will disconnect G. The twisted hypercube H n is a new variant of hypercubes with asymptotically optimal diameter introduced by Zhu. In this paper, we will determine both κ ( H n; T ) and κ s ( H n; T ) for T ∈ { K 1, r, P k }, respectively, where 3 ≤ r ≤ 4 and 1 ≤ k ≤ n.

Details DOI

EAAI Journal 2016 Journal Article

A boundary-fixed negative selection algorithm with online adaptive learning under small samples for anomaly detection

  • Dong Li
  • Shulin Liu
  • Hongli Zhang

The traditional negative selection algorithm (NSA) lacks online adaptive learning ability, and this restricts its application range. A new NSA, boundary-fixed negative selection algorithm with online adaptive learning under small samples (OALFB-NSA), is proposed in this paper. Boundary-fixed negative selection algorithm (FB-NSA) generates a layer of detectors, which are around the self space. These detectors are only related to the training samples, and have nothing to do with the training times. OALFB-NSA detectors can adapt themselves to real-time variety of self space during the testing stage. Experimental comparison among FB-NSA, V-detector and other anomaly detection algorithms on Iris data sets and biomedical dataset shows that the FB-NSA can obtain the higher detection rate and lower false alarm rate in most cases. The experimental comparison between OALFB-NSA, interface detector with online adaptive learning under small training samples (OALI-detector) and V-detector on Iris data sets shows that when overfitting does not occur, the OALFB-NSA can obtain the higher detection rate and lower false alarm rate, even if only one self sample is used for training.

Details DOI

STOC Conference 2008 Conference Paper

A quadratic lower bound for the permanent and determinant problem over any characteristic! = 2

  • Jin-Yi Cai
  • Xi Chen 0001
  • Dong Li

In Valiant's theory of arithmetic complexity, the classes VP and VNP are analogs of P and NP. A fundamental problem concerning these classes is the Permanent and Determinant Problem: Given a field F of characteristic ≠2, and an integer n, what is the minimum m such that the permanent of an n x n matrix X=(x ij ) can be expressed as a determinant of an m x m matrix, where the entries of the determinant matrix are affine linear functions of x ij 's, and the equality is in F [X]. Mignon and Ressayre (2004) [11] proved a quadratic lower bound m=Ω(n 2 ) for fields of characteristic 0. We extend the Mignon-Ressayre quadratic lower bound to all fields of characteristic ≠2.

Details

ICRA Conference 1992 Conference Paper

A control design approach for slew maneuver of elastic multibody systems

  • Dong Li

The author presents an approach to control design for slew maneuver of a class of elastic multibody systems. The approach is based on dynamic decoupling through input-output feedback linearization and subsequent independent trajectory control of each individual body. Stability and performance (in both tracking and vibration suppression) of the control system are maintained at all system configurations and with maneuvers of different speeds. >

Details

ICRA Conference 1987 Conference Paper

Force control of direct-drive manipulators for surface following

  • Kamal Youcef-Toumi
  • Dong Li

The surface following by a robot arm is investigated in this paper. The goal is to present control strategies so that the arm can follow a surface at a given speed with desired contact force. First, a discussion on the use of direct-drive manipulators with decoupled and invariant dynamics is given. These are shown to be suitable for such force control applications. In this case, the controller design in either joint space or end effector space would involve nonlinearities due to kinematics only. This would reduce the computation burden and allows for high performance since the kinematic parameters can be estimated with better accuracies than dynamic parameters. Second, to have a better understanding of some fundamental characteristics of force control, such as the effects of actuator dynamics, environment/sensor stiffness on the performance, experiments were done using a one degree-of-freedom direct-drive arm. The use of a high gain inner velocity loop is shown to give the force control good command following and disturbance rejection characteristics. The direct-drive manipulator shows a superior performance over conventional systems as a result of fast actuator dynamics, low friction and no mechanical backlash. The experiments are conducted to investigate the force speed of response and steady state behavior, impact control and surface following performance.

Details
v2026.09.13