Liang Li

AAAI Conference 2026 Conference Paper

EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation

• Shuhao Han
• Haotian Fan
• Jiachen Fu
• Liang Li
• Tao Li
• Junhui Cui
• Yunqiu Wang
• Yang Tai

Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated methods emerge to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated methods is constrained by the limited scale of existing datasets. Additionally, existing datasets lack the capacity to assess the performance of automated methods at a fine-grained level. In this study, we contribute an EvalMuse-40K dataset, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our dataset. This allows us to comprehensively evaluate the performance of image-text alignment methods for T2I models. Based on this dataset, we introduce an efficient automated evaluation method termed FGA-BLIP2, which enables Fine-Grained Alignment evaluation solely by inputting images and text leveraging BLIP2, without visual question answering for each fine-grained element. Experimental results show the proposed FGA-BLIP2 efficiently achieves good performance on multiple image-text alignment datasets. Meanwhile, benefiting from the high efficiency and fine-grained evaluation capability of FGA-BLIP2, we apply it as a reward model to improve text-to-image models, which effectively enhances the image-text alignment ability of text-to-image models.

AAAI Conference 2026 Conference Paper

Forgetting Knowledge Localization and Isolation for Continual Forgetting of Pre-trained Vision Models

• Zhiwen Yang
• Jiehua Zhang
• Chenggang Yan
• Yuhan Gao
• Zongpeng Li
• Xichun Sheng
• Liang Li

Continual forgetting task aims to continuously remove multiple target knowledge subsets from pre-trained models while maintaining the integrity of remaining knowledge. Existing methods suffer from both incomplete forgetting of target knowledge and unintended forgetting of indistinguishable remaining knowledge. To address these challenges, we propose the forgetting knowledge localization and isolation for continual forgetting in pre-trained vision models which precisely forgets target knowledge while reducing over-forgetting of remaining knowledge. To achieve precise forgetting, we first propose the forgetting knowledge layer localization to explore layers in the model which are more related to forgetting knowledge. Then, we design the forgetting knowledge parameter isolation to isolate the parameters sensitive to forgetting knowledge in these selected layers, mitigating over-forgetting of remaining knowledge. Finally, we fine-tune these isolated parameters and freeze the remaining parameters to achieve efficient forgetting while maintaining high performance on retained datasets. Extensive experimental results demonstrate that our method achieves superior performance over state-of-the-art methods across multiple continual forgetting tasks.

AAAI Conference 2026 Conference Paper

InstructDubber: Instruction-based Alignment for Zero-shot Movie Dubbing

• Zhedong Zhang
• Liang Li
• Gaoxiang Cong
• Chunshan Liu
• Yuhan Gao
• Xiaowan Wang
• Tao Gu
• Yuankai Qi

Movie dubbing seeks to synthesize speech from a given script using a specific voice, while ensuring accurate lip synchronization and emotion-prosody alignment with the character’s visual performance. However, existing alignment approaches based on visual features face two key limitations: (1) they rely on complex, handcrafted visual preprocessing pipelines, including facial landmark detection and feature extraction; and (2) they generalize poorly to unseen visual domains, often resulting in degraded alignment and dubbing quality. To address these issues, we propose InstructDubber, a novel instruction-based alignment dubbing method for both robust in-domain and zero-shot movie dubbing. Specifically, we first feed the video, script, and corresponding prompts into a multimodal large language model to generate natural language dubbing instructions regarding the speaking rate and emotion state depicted in the video, which is robust to visual domain variations. Second, we design an instructed duration distilling module to mine discriminative duration cues from speaking rate instructions to predict lip-aligned phoneme-level pronunciation duration. Third, for emotion-prosody alignment, we devise an instructed emotion calibrating module, which fine-tunes an LLM-based instruction analyzer using ground truth dubbing emotion as supervision and predicts prosody based on the calibrated emotion analysis. Finally, the predicted duration and prosody, together with the script, are fed into the audio decoder to generate video-aligned dubbing. Extensive experiments on three major benchmarks demonstrate that InstructDubber outperforms state‑of‑the‑art approaches across both in‑domain and zero‑shot scenarios.

AAAI Conference 2026 Conference Paper

STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models

• Jingjing Zhou
• Gaoxiang Cong
• Li Su
• Liang Li

Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risks, as sensitive information may be deeply embedded throughout the reasoning process. Existing Large Language Models (LLMs) unlearning approaches that typically focus on modifying only final answers are insufficient for LRMs, as they fail to remove sensitive content from intermediate steps, leading to persistent privacy leakage and degraded security. To address these challenges, we propose Sensitive Trajectory Regulation (STaR), a parameter-free, inference-time unlearning framework that achieves robust privacy protection throughout the reasoning process. Specifically, we first identify sensitive content via semantic-aware detection. Then, we inject global safety constraints through secure prompt encoder. Next, we perform trajectory-aware suppression to dynamically block sensitive content across the entire reasoning chain. Finally, we apply token-level adaptive filtering to prevent both exact and paraphrased sensitive tokens during generation. Furthermore, to overcome the inadequacies of existing evaluation protocols, we introduce two metrics: Multi-Decoding Consistency Assessment (MCS), which measures the consistency of unlearning across diverse decoding strategies, and Multi-Granularity Membership Inference Attack (MIA) Evaluation, which quantifies privacy protection at both answer and reasoning-chain levels. Experiments on the R-TOFU benchmark demonstrate that STaR achieves comprehensive and stable unlearning with minimal utility loss, setting a new standard for privacy-preserving reasoning in LRMs.

AAAI Conference 2026 Conference Paper

Temporal Calibrating and Distilling for Scene-Text Aware Text-Video Retrieval

• Zhiqian Zhao
• Liang Li
• Lei Shen
• Xichun Sheng
• Yaoqi Sun
• Fang Kang
• Chenggang Yan

Existing text-video retrieval methods mainly focus on singlemodal video content (i.e., visual entities), often overlooking heterogeneous scene text that is ubiquitous in human environments. Although scene text in videos provides finegrained semantics for cross-modal retrieval, effectively utilizing it presents two key challenges: (1) Temporally dense scene text disrupts sync with sparse video frames, obstructing video understanding;(2) Redundant scene text and irrelevant video frames hinder the learning of discriminative temporal clues for retrieval. To address them, we propose a temporal scene-text calibrating and distilling (TCD) network for textvideo retrieval. Specifically, we first design a window-OCR captioner that aggregates dense scene text into OCR captions to facilitate feature interaction. Next, we devise a heterogeneous semantics calibration module that leverages scene text as a self-supervised signal to temporally align window-level OCR captions and frame-level video features. Further, we introduce a context-guided temporal clue distillation module to learn the complementary and relevant details between scene text and video modalities, thereby obtaining discriminative temporal clues for retrieval. Extensive experiments show that our TCD achieves state-of-the-art performance on three scene-text related benchmarks.

I&C Journal 2026 Journal Article

Variable version Lovász local lemma: A tale of two boundaries

• Kun He
• Liang Li
• Xingwu Liu
• Yuyi Wang
• Mingji Xia

Shearer gave a tight criterion for the abstract version of the Lovász Local Lemma (abstract-LLL), but the corresponding picture for the variable version (variable-LLL), where events are generated from independent random variables, has remained largely open. We establish a necessary and sufficient criterion for variable-LLL expressed purely in terms of the event probabilities and the event-variable bigraph. This allows us to determine exactly the probability boundary for two fundamental families of event-variable graphs: cyclic and treelike bigraphs, giving the first nontrivial cases where the variable-LLL boundary is fully characterized. As a byproduct, we obtain a general constructive procedure that, for any given probability vector and event-variable graph, produces a set of events whose union has maximum possible probability; the method also applies when any two events are either independent or disjoint. We further show that computing the variable-LLL boundary is #P-hard in general, and focus on deciding whether there is a gap between the variable-LLL boundary and the corresponding abstract-LLL (Shearer) boundary. We prove that gap existence can be decided without evaluating Shearer's condition or our criterion. Using this theorem, we show that there is no gap when the base graph of the event-variable graph is a tree, whereas any induced cycle of length at least four forces a gap. Finally, we develop reduction rules that propagate gapful/gapless property and apply them to several combinatorial event-variable graphs.

ICML Conference 2025 Conference Paper

AEQA-NAT: Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation

• Xiangyu Qu
• Guojing Liu
• Liang Li

Non-autoregressive Transformers (NATs) have garnered significant attention due to their efficient decoding compared to autoregressive methods. However, existing conditional dependency modeling schemes based on masked language modeling introduce a training-inference gap in NATs. For instance, while NATs sample target words during training to enhance input, this condition cannot be met during inference, and simply annealing the sampling rate to zero during training leads to model performance degradation. We demonstrate that this training-inference gap prevents NATs from fully realizing their potential. To address this, we propose an adaptive end-to-end quantization alignment training framework, which introduces a semantic consistency space to adaptively align NAT training, eliminating the need for target information and thereby bridging the training-inference gap. Experimental results demonstrate that our method outperforms most existing fully NAT models, delivering performance on par with Autoregressive Transformer (AT) while being 17. 0 times more efficient in inference.

EAAI Journal 2025 Journal Article

An evacuation guidance approach based on multi-agent shared Q-learning

• Yanbin Han
• Hong Liu
• Liang Li
• Wenhao Li

Crowd evacuation dynamics have garnered significant research attention in recent years due to their critical impact on public safety. Guided evacuation systems have emerged as a promising solution for optimizing evacuation time and enhancing evacuation efficiency in emergency scenarios. To address these challenges, this study proposes a novel multi-agent collaborative evacuation guidance framework utilizing shared Q-learning. The proposed architecture employs coordinated agents to direct pedestrian flows toward exits through strategic cooperation. Specifically, we implement a group-based evacuation mechanism where only designated leaders receive optimized routing instructions, thereby minimizing haphazard movements among crowd members. To enable effective path planning, our system synthesizes localized evacuation data into comprehensive global information through multi-agent knowledge sharing, thereby generating optimized paths for leaders. To evaluate a path, we define a reward function incorporating four key factors: distance, density, traveling time, and selection frequency of route sections. A path-planning algorithm is developed to provide paths with a high reward for evacuees. Furthermore, to validate the proposed framework, a reciprocal velocity obstacle (RVO) model is employed to simulate crowd dynamics during evacuations. The experimental results demonstrate that the approach can shorten the total evacuation time and promote the balanced utilization of all available exits.

IROS Conference 2025 Conference Paper

Collective Behavior Clone with Visual Attention via Neural Interaction Graph Prediction

• Kai Li
• Zhao Ma
• Liang Li
• Shiyu Zhao 0002

In this paper, we propose a framework, collective behavioral cloning (CBC), to learn the underlying interaction mechanism and control policy of a swarm system. Given the trajectory data of a swarm system, we propose a graph variational autoencoder (GVAE) to learn the local interaction graph. Based on the interaction graph and swarm trajectory, we use behavioral cloning to learn the control policy of the swarm system. To demonstrate the practicality of CBC, we deploy it on a real-world decentralized vision-based robot swarm system. A visual attention network is trained based on the learned interaction graph for online neighbor selection. Experimental results show that our method outperforms previous approaches in predicting both the interaction graph and swarm actions with higher accuracy. This work offers a promising approach for understanding interaction mechanisms and swarm dynamics in future swarm robotics research. Code and data are available 6.

EAAI Journal 2025 Journal Article

Cross-domain fault diagnosis of marine diesel engines based on stepwise diffusion and iterative bidirectional optimization

• Zhen Zhao
• Ziru Jin
• Xin Xin
• Yutong Fu
• Xiaotong Huang
• Liang Li
• Hongyan Qin
• Chong Wei

Cross-domain fault diagnosis of marine diesel engines presents significant challenges due to variations in data distribution and the limited availability of labeled fault samples under different operating conditions. To address this, an unsupervised domain-adaptive diagnostic framework is proposed, integrating stepwise diffusion and iterative bidirectional optimization to enhance fault identification. First, the quadratic axial attention transformer introduces a fourth weight in the axial computation to effectively capture the long-range spatio-temporal correlations in the time–frequency representations and strengthen the cross-axis contextual dependence. Next, the domain stepwise diffusion bridge utilizes Markov transform to gradually refine the significant distributional differences across domains into continuous sub-distributions, ensuring a smoother adaptation process. Finally, an iterative bidirectional optimization strategy is proposed to dynamically coordinate the interaction between stepwise diffusion and fault classification, where two complementary learning directions are alternately executed to preserve the semantic integrity of features. Experimental validation on a self-constructed dataset covering multiple operating conditions demonstrates the effectiveness of the proposed approach, achieving 93. 80 % average accuracy, 93. 75 % precision, and 93. 45 % recall. This approach not only breaks through the limitations of existing domain alignment methods and provides a brand new solution for cross-domain fault diagnosis, but also provides a wide range of implications for future research and applications in this field. The code and model are available at: https: //github. com/lazyJzr/UDAtask.

AAAI Conference 2025 Conference Paper

DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy

• Xi Wang
• Xueyang Fu
• Liang Li
• Zheng-Jun Zha

Despite the advanced long-sequence modeling of Mamba, which has expanded its applications in image restoration, there remains a lack of exploration combining its strengths with the specific characteristics of JPEG image restoration, where high-frequency components are lost after the Discrete Cosine Transform (DCT). To address this, we introduce DCTMamba, a new framework designed to apply Mamba more effectively to JPEG image restoration. Specifically, our method integrates the Discrete Cosine Transform (DCT) into the Mamba to establish the sequential scanning from lower to higher frequencies, enabling the network to initially reconstruct coarse structures and progressively refine the image with more intricate details. Furthermore, recognizing the variable frequency distributions that arise from DCT transformations across different image sizes, we have developed Scale-Adaptive Normalization to manage these variations adeptly. Comprehensive experiments confirm that DCTMamba significantly outperforms existing solutions, achieving high fidelity in both coarse structures and fine details.CTMamba significantly outperforms existing solutions, achieving high fidelity in both coarse structures and fine details.

IROS Conference 2025 Conference Paper

DHC-ME: A Decentralized Hybrid Cooperative Approach for Multi-Robot Autonomous Exploration

• Wenhao Jia
• Yang Xu
• Chenglong Qian
• Xiufang Shi
• Jiming Chen
• Liang Li

Multi-robot exploration in unknown environments is a fundamental task for multi-robot systems, which requires the coordination of the robots to avoid collisions and conflicts while performing task allocation. Existing exploration strategies improve the efficiency of multi-robot exploration by modeling the multi-robot task allocation problem as a variant of the multiple traveling salesman problem. However, this is computationally intensive and difficult to deploy on physical platforms. Hence, this paper develops a hybrid strategy for range-sensing multi-robot exploration with effective team coordination, enabling a larger team dispersion degree and higher exploration efficiency. In addition, we present a novel multi-robot exploration point detection method suitable for narrow and dynamic environments, effectively reducing exploration failure and incompleteness. The Gazebo simulations demonstrate better exploration efficiency and the least time cost of our exploration framework compared with state-of-the-art methods, and real-world experiments also validate the effectiveness. The code is released at https://github.com/NeSC-IV/DHC_ME.

NeurIPS Conference 2025 Conference Paper

Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection

• Junxi Chen
• Liang Li
• Yunbin Tu
• Li Su
• Zhe Xue
• Qingming Huang

Video Anomaly Detection (VAD) aims to identify abnormal frames from discrete events within video sequences. Existing VAD methods suffer from heavy annotation burdens in fully-supervised paradigm, insensitivity to subtle anomalies in semi-supervised paradigm, and vulnerability to noise in weakly-supervised paradigm. To address these limitations, we propose a novel paradigm: Single-Frame supervised VAD (SF-VAD), which uses a single annotated abnormal frame per abnormal video. SF-VAD ensures annotation efficiency while offering precise anomaly reference, facilitating robust anomaly modeling, and enhancing the detection of subtle anomalies in complex visual contexts. To validate its effectiveness, we construct three SF-VAD benchmarks by manually re-annotating the ShanghaiTech, UCF-Crime, and XD-Violence datasets in a practical procedure. Further, we devise Frame-guided Progressive Learning (FPL), to generalize sparse frame supervision to event-level anomaly understanding. FPL first leverages evidential learning to estimate anomaly relevance guided by annotated frames. Then it extends anomaly supervision by mining discrete abnormal events based on anomaly relevance and feature similarity. Meanwhile, FPL decouples normal patterns by isolating distinct normal frames outside abnormal events, reducing false alarms. Extensive experiments show SF-VAD achieves state-of-the-art detection results while offering a favorable trade-off between performance and annotation cost.

AAAI Conference 2025 Conference Paper

Heterogeneous Prompt-Guided Entity Inferring and Distilling for Scene-Text Aware Cross-Modal Retrieval

• Zhiqian Zhao
• Liang Li
• Jiehua Zhang
• Yaoqi Sun
• Xichun Sheng
• Haibing Yin
• Shaowei Jiang

In cross-modal retrieval, comprehensive image understanding is vital while the scene text in images can provide fine-grained information to understand visual semantics. Current methods fail to make full use of scene text. They suffer from the semantic ambiguity of independent scene text and overlook the heterogeneous concepts in image-caption pairs. In this paper, we propose a heterogeneous prompt-guided entity inferring and distilling (HOPID) network to explore the nature connection of scene text in images and captions and learn a property-centric scene text representation. Specifically, we propose to align scene text in images and captions via heterogeneous prompt, which consists of visual and text prompt. For text prompt, we introduce the discriminative entity inferring module to reason key scene text words from captions, while visual prompt highlights the corresponding scene text in images. Furthermore, to secure a robust scene text representation, we design a perceptive entity distilling module that distills the beneficial information of scene text at a fine-grained level. Extensive experiments show that the proposed method significantly outperforms existing approaches on two public cross-modal retrieval benchmarks.

NeurIPS Conference 2025 Conference Paper

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization

• Zhenpeng Huang
• Jiaqi Li
• Zihan Jia
• Xinhao Li
• Desen Meng
• Lingxue Song
• Xi Chen
• Liang Li

We present LongVPO, a novel two‑stage Direct Preference Optimization framework that enables short‑context vision‑language models to robustly understand ultra‑long videos without any long‑video annotations. In Stage 1, we synthesize preference triples by anchoring questions to individual short clips, interleaving them with distractors, and applying visual‑similarity and question‑specificity filtering to mitigate positional bias and ensure unambiguous supervision. We also approximate the reference model’s scoring over long contexts by evaluating only the anchor clip, reducing computational overhead. In Stage 2, we employ a recursive captioning pipeline on long videos to generate scene-level metadata, and then use a large language model to craft multi-segment reasoning queries and dispreferred responses, aligning the model's preferences through multi-segment reasoning tasks. With only 16K synthetic examples and no costly human labels, \model{} outperforms the state‑of‑the‑art open‑source models on multiple long‑video benchmarks, while maintaining strong short‑video performance (e. g. , on MVBench), offering a scalable paradigm for efficient long‑form video understanding.

IROS Conference 2025 Conference Paper

Method for Sensing Lateral Force and Skidding on the Tool Tip in Surgical Robot Deep Bone Drilling *

• Zheyu Chen 0010
• Liang Li

Bone drilling is a critical component of many clinical surgeries. In robot-assisted deep bone drilling procedures, the complex structure of bone tissue and individual variations in drilling paths often cause slender tools to skid on personalized bone surfaces, leading to deviations that significantly impact surgical precision and safety. This paper presents the development of an orthopedic surgical robot equipped with skidding sensing capabilities. A novel sensing solution for the bone drilling unit is proposed, which employs rigid body force transmission and decouples thrust and lateral force sensing. This approach addresses the challenge of acquiring force information from the deep tool tip within the body. We also introduce a tool tip skidding estimation method based on the deflection curve model and the Spatial-Beam Constraint Model (SBCM). A specialized simulation device for measuring tool tip offset and force was designed. The experimental results demonstrate that the system achieves average sensing errors of 31. 8 mN and 43. 5 mN for lateral forces at the tool tip along the X and Y directions, respectively. Additionally, the system's resolution for skidding estimation reaches 0. 2 mm. Real bone drilling experiments confirm the system’s ability to effectively provide feedback on skidding during surgery. The proposed method enhances the safety of orthopedic surgical robots and offers crucial sensing information for lateral forces and skidding, paving the way for future autonomous bone drilling procedures.

IROS Conference 2025 Conference Paper

PB-MOT: Pose-aware Association Boosted Online 3D Multi-Object Tracking

• Bo Pang
• Yang Xu
• Jiming Chen
• Liang Li

Robotic and autonomous driving platforms necessitate efficient 3D Multi-Object Tracking (MOT) that harmonizes geometric precision, motion robustness, and computational efficiency. Traditional 3D MOT approaches face critical challenges: geometric similarity metrics (e. g. , IoU-based) degrade at long ranges with high computational costs, while distance-based methods fail to capture object orientation and shape; the effects of occlusion and the intricate relative ego-object motion degrade tracking performance in dynamic scenes. To this end, we propose PB-MOT, an online framework integrating two key innovations: ego-motion-compensated state estimation that decouples dynamic interactions; and a rotated ellipse association algorithm unifying pose and shape-aware matching with adaptive distance constraints. Evaluations on the KITTI benchmark show that our PB-MOT achieves state-of-the-art performance with a HOTA score of 81. 94%, while running at an impressive 2, 402. 76 FPS on CPU. This enables real-time, high-fidelity perception and tracking for resource-constrained robotic systems.

AAAI Conference 2025 Conference Paper

Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning

• Yunbin Tu
• Liang Li
• Li Su
• Qingming Huang

Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval, and leverages it as a feature extractor for other three challenging tasks solved in a multi-task learning paradigm. Nevertheless, this work struggles to learn the comprehensive cognition of user-preferred content, due to disregarding the hierarchies and association relations across modalities. In this paper, guided by the shallow-to-deep principle, we propose a query-centric audio-visual cognition (QUAG) network to construct a reliable multi-modal representation for moment retrieval, segmentation and step-captioning. Specifically, we first design the modality-synergistic perception to obtain rich audio-visual content, by modeling global contrastive alignment and local fine-grained interaction between visual and audio modalities. Then, we devise the query-centric cognition that uses the deep-level query to perform the temporal-channel filtration on the shallow-level audio-visual representation. This can cognize user-preferred content and thus attain a query-centric audio-visual representation for three tasks. Extensive experiments show QUAG achieves the SOTA results on HIREST. Further, we test QUAG on the query-based video summarization task and verify its good generalization.

AAAI Conference 2025 Conference Paper

Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning

• Rong Li
• Liang Li
• Jiehua Zhang
• Qiang Zhao
• Hongkui Wang
• Chenggang Yan

Change captioning aims to describe the differences between two similar images using natural language, significantly aiding in understanding and monitoring changes. This challenging task requires a fine-grained understanding of subtle changes while resisting disturbances like viewpoint shifts and illumination variations. Existing methods often rely solely on global difference features and lack comprehensive alignment of linguistic and visual information, leading to overlooking fine-grained details and generating semantic hallucinated sentences. To address these limitations, we propose the region-aware difference distilling (RDD) network with attribute-guided contrastive regularization (ACR). The RDD uses global difference features to progressively distill regional difference features using learnable vectors, allowing for more precise identification of changed regions. The ACR enhances comprehensive alignment between linguistic and visual information by formulating Nouns-to-Objects (N2O) and Verbs-to-Actions (V2A) alignment losses to regularize the regional difference features. Promising results on three datasets demonstrate that our method outperforms the state-of-the-art change captioning methods.

ICRA Conference 2025 Conference Paper

Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture

• Wangtao Lu
• Yufei Wei
• Jiadong Xu
• Wenhao Jia
• Liang Li
• Rong Xiong
• Yue Wang 0020

Automatic parameter tuning methods for planning algorithms, which integrate pipeline approaches with learning-based techniques, are regarded as promising due to their stability and capability to handle highly constrained environments. While existing parameter tuning methods have demonstrated considerable success, further performance improvements require a more structured approach. In this paper, we propose a hierarchical architecture for reinforcement learning-based parameter tuning. The architecture introduces a hierarchical structure with low-frequency parameter tuning, mid-frequency planning, and high-frequency control, enabling concurrent enhancement of both upper-layer parameter tuning and lower-layer control through iterative training. Experimental evaluations in both simulated and real-world environments show that our method surpasses existing parameter tuning approaches. Furthermore, our approach achieves first place in the Benchmark for Autonomous Robot Navigation (BARN) Challenge.

IJCAI Conference 2025 Conference Paper

SSTrack: Sample-interval Scheduling for Lightweight Visual Object Tracking

• Yutong Kou
• Shubo Lin
• Liang Li
• Bing Li
• Weiming Hu
• Jin Gao

In recent years, CPU real-time object tracking has gained significant attention due to its broad applications such as UAV-tracking. To maintain computational efficiency, most existing CPU real-time object trackers rely on lightweight backbones and employ a single initial template image without intermediate online templates. Although the appearance variance between the template and the search is larger under this single template setting, the representation ability of lightweight backbones is weaker which poses a challenge when training lightweight object trackers. To address this issue, we propose SSTrack, a new easier-to-harder training schedule for the lightweight object tracker. From the data perspective, our method designed a success-aware sample scheduler that gradually increases difficult training samples with longer template-search time intervals and reduces the amount of the easier samples so the training cost remains unchanged. From the optimization perspective, we utilized a gradient scaling strategy that retains the original training objective of easier samples despite the reduction in their quantities. With the collective effort from both perspectives, our method achieves State-of-the-Art CPU-real-time accuracy on 5 UAV-tracking benchmarks and 5 general object tracking benchmarks. Codes and models will be available at https: //github. com/Kou-99/SSTrack.

AAAI Conference 2025 Conference Paper

Union Is Strength! Unite the Power of LLMs and MLLMs for Chart Question Answering

• Jiapeng Liu
• Liang Li
• Shihao Rao
• Xiyan Gao
• Weixin Guan
• Bing Li
• Can Ma

Chart Question Answering (CQA) requires models to perform chart perception and reasoning. Recent studies driven by Large Language Models (LLMs) have dominated CQA. These include employing more cognitively capable LLMs for indirectly reasoning over transformed charts, i.e., tables, and directly perceiving charts utilizing Multimodal Large Language Models (MLLMs) with a wider perceptual range. Yet, they often encounter bottlenecks due to the limitation of the receptive field of LLMs and the fragility of the complex reasoning of some MLLMs. To unite the strengths of LLMs and MLLMs to complement each other's limitations, we propose Synergy, a framework that unites the power of both models for CQA. Synergy first unites the chart with a table as the augmented perceptual signal. Next, it unites LLMs and MLLMs, scheduling the former to decompose a question into subquestions and the latter to answer these by perceiving the chart. Lastly, it operates LLMs to summarize the subquestion-answer pairs to refine the final answer. Extensive experimental results on popular CharQA and PlotQA benchmarks reveal that, with the power of union, Synergy outperforms strong competitors and achieves superior boosts over naive MLLMs by uniting them with a smaller LLM.

AAAI Conference 2025 Conference Paper

WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling

• Huai-An Su
• Jiaxiang Geng
• Liang Li
• Xiaoqi Qin
• Yanzhao Hou
• Hao Wang
• Xin Fu
• Miao Pan

As a popular distributed learning paradigm, federated learning (FL) over mobile devices fosters numerous applications, while their practical deployment is hindered by participating devices' computing and communication heterogeneity. Some pioneering research efforts proposed to extract subnetworks from the global model, and assign as large a subnetwork as possible to the device for local training based on its full computing capacity. Although such fixed size subnetwork assignment enables FL training over heterogeneous mobile devices, it is unaware of (i) the dynamic changes of devices' communication and computing conditions and (ii) FL training progress and its dynamic requirements of local training contributions, both of which may cause very long FL training delay. Motivated by those dynamics, in this paper, we develop a wireless and heterogeneity aware latency efficient FL (WHALE-FL) approach to accelerate FL training through adaptive subnetwork scheduling. Instead of sticking to the fixed size subnetwork, WHALE-FL introduces a novel subnetwork selection utility function to capture device and FL training dynamics, and guides the mobile device to adaptively select the subnetwork size for local training based on (a) its computing and communication capacity, (b) its dynamic computing and/or communication conditions, and (c) FL training status and its corresponding requirements for local training contributions. Our evaluation shows that, compared with peer designs, WHALE-FL effectively accelerates FL training without sacrificing learning accuracy.

NeurIPS Conference 2024 Conference Paper

A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration

• Renlang Huang
• Yufan Tang
• Jiming Chen
• Liang Li

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically sparse and loose without consideration of geometric consistency, which makes the subsequent fine matching rely on ineffective optimal transport and hypothesis-and-selection methods for consistency. Therefore, these methods are neither efficient nor scalable for real-time applications such as odometry in robotics. To address these issues, we design a consistency-aware spot-guided Transformer (CAST), which incorporates a spot-guided cross-attention module to avoid interfering with irrelevant areas, and a consistency-aware self-attention module to enhance matching capabilities with geometrically consistent correspondences. Furthermore, a lightweight fine matching module for both sparse keypoints and dense features can estimate the transformation accurately. Extensive experiments on both outdoor LiDAR point cloud datasets and indoor RGBD point cloud datasets demonstrate that our method achieves state-of-the-art accuracy, efficiency, and robustness.

YNIMG Journal 2024 Journal Article

Harmonizing three-dimensional MRI using pseudo-warping field guided GAN

• Jiaying Lin
• Zhuoshuo Li
• Youbing Zeng
• Xiaobo Liu
• Liang Li
• Neda Jahanshad
• Xinting Ge
• Dan Zhang

In pursuit of cultivating automated models for magnetic resonance imaging (MRI) to aid in diagnostics, an escalating demand for extensive, multisite, and heterogeneous brain imaging datasets has emerged. This potentially introduces biased outcomes when directly applied for subsequent analysis. Researchers have endeavored to address this issue by pursuing the harmonization of MRIs. However, most existing image-based harmonization methods for MRI are tailored for 2D slices, which may introduce inter-slice variations when they are combined into a 3D volume. In this study, we aim to resolve inconsistencies between slices by introducing a pseudo-warping field. This field is created randomly and utilized to transform a slice into an artificially warped subsequent slice. The objective of this pseudo-warping field is to ensure that generators can consistently harmonize adjacent slices to another domain, without being affected by the varying content present in different slices. Furthermore, we construct unsupervised spatial and recycle loss to enhance the spatial accuracy and slice-wise consistency across the 3D images. The results demonstrate that our model effectively mitigates inter-slice variations and successfully preserves the anatomical details of the images during the harmonization process. Compared to generative harmonization models that employ 3D operators, our model exhibits greater computational efficiency and flexibility.

ICRA Conference 2024 Conference Paper

Hydrodynamic Interactions in Schooling Fish: Prioritizing Real Fish Kinematics Over Travelling-wavy Undulation

• Li-Ming Chao
• Liang Li

Hydrodynamic interactions are crucial for understanding fish movement, particularly within the realm of robotic applications. Traditionally, many studies have favoured simplified travelling-wavy undulations derived from observed real fish kinematics. This approach often neglects higher-order undulations, thereby missing the subtleties of authentic fish movements. In this study, we utilised Computational Fluid Dynamics (CFD) to investigate the implications of using real fish kinematics in hydrodynamic interactions among schooling fish. We analysed two scenarios: one driven by real fish kinematics in spatiotemporal formations, and the other by travelling-wavy undulations inferred from the same real fish kinematics. Our results highlight the advantages of using real fish body kinematics for a more accurate representation of hydrodynamics in fish swimming. In contrast, the idealised travelling-wavy undulations tend to apply excessive force, displacing real fish more than expected. Additionally, the vortices and corresponding flow fields generated by real fish kinematics were found to be more stable than those arising from simplified travelling-wavy undulations. Our study underscores the significance of integrating real fish kinematics into robotic fish design and hydrodynamic studies in schooling fish.

ICRA Conference 2024 Conference Paper

iBoW3D: Place Recognition Based on Incremental and General Bag of Words in 3D Scans

• Yuxiaotong Lin
• Jiming Chen
• Liang Li

Existing methods for place recognition in 3D point clouds either ignore partial structure information by converting 3D scans to 2D images or construct constrained bag-of-words (BoW) representations reliant on specific feature extraction algorithms. In this paper, we propose a novel method based on incremental and general bag of words. Incorporating an adaptable keypoint and 3D local feature extraction method, we employ an incremental BoW model that is updated regularly. This enables a coarse-to-fine candidate selection from the database. And a revisit can be identified following geometric verification. In addition, we propose a new supplementary metric that addresses the leaving-out issue of the conventional metric, enhancing the identification of true loops. Employing a state-of-the-art (SOTA) keypoint and feature extraction algorithm, we evaluate our method as well as SOTA place recognition methods using diverse datasets with varying qualities. Experimental results demonstrate that our method outperforms the baselines across all three datasets, showcasing robust performance and notable generalization capabilities.

ICRA Conference 2024 Conference Paper

KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping

• Renlang Huang
• Minglei Zhao
• Jiming Chen
• Liang Li

Sparse keypoint matching based on distinct 3D feature representations can improve the efficiency and robustness of point cloud registration. Existing learning-based 3D descriptors and keypoint detectors are either independent or loosely coupled, so they cannot fully adapt to each other. In this work, we propose a tightly coupled keypoint detector and descriptor (TCKDD) based on a multi-task fully convolutional network with a probabilistic detection loss. In particular, this self-supervised detection loss fully adapts the keypoint detector to any jointly learned descriptors and benefits the self-supervised learning of descriptors. Extensive experiments on both indoor and outdoor datasets show that our TCKDD achieves state-of- the-art performance in point cloud registration. Furthermore, we design a keypoint detector and descriptors-assisted LiDAR odometry and mapping framework (KDD-LOAM), whose real-time odometry relies on keypoint descriptor matching-based RANSAC. The sparse keypoints are further used for efficient scan-to-map registration and mapping. Experiments on KITTI dataset demonstrate that KDD-LOAM significantly surpasses LOAM and shows competitive performance in odometry.

ICRA Conference 2024 Conference Paper

LESS-Map: Lightweight and Evolving Semantic Map in Parking Lots for Long-term Self-Localization

• Mingrui Liu
• Xinyang Tang
• Yeqiang Qian
• Jiming Chen
• Liang Li

Precise and long-term stable localization is essential in parking lots for tasks like autonomous driving or autonomous valet parking, etc. Existing methods rely on a fixed and memory-inefficient map, which lacks robust data association approaches. And it is not suitable for precise localization or long-term map maintenance. In this paper, we propose a novel mapping, localization, and map update system based on ground semantic features, utilizing low-cost cameras. We present a precise and lightweight parameterization method to establish improved data association and achieve accurate localization at centimeter-level. Furthermore, we propose a novel map update approach by implementing high-quality data association for parameterized semantic features, allowing continuous map update and refinement during re-localization, while maintaining centimeter-level accuracy. We validate the performance of the proposed method in real-world experiments and compare it against state-of-the-art algorithms. The proposed method achieves an average accuracy improvement of 5cm during the registration process. The generated maps consume only a compact size of 450 KB/km and remain adaptable to evolving environments through continuous update.

NeurIPS Conference 2024 Conference Paper

Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning

• Jiadong Pan
• Hongcheng Gao
• Zongyu Wu
• Taihang Hu
• Li Su
• Qingming Huang
• Liang Li

Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful images but such external filters do not inherently detoxify the model and can be easily bypassed. Hence, model unlearning and data cleaning are the most essential methods for maintaining the safety of models, given their impact on model parameters. However, malicious fine-tuning can still make models prone to generating harmful or undesirable images even with these methods. Inspired by the phenomenon of catastrophic forgetting, we propose a training policy using contrastive learning to increase the latent space distance between clean and harmful data distribution, thereby protecting models from being fine-tuned to generate harmful images due to forgetting. The experimental results demonstrate that our methods not only maintain clean image generation capabilities before malicious fine-tuning but also effectively prevent DMs from producing harmful images after malicious fine-tuning. Our method can also be combined with other safety methods to maintain their safety against malicious fine-tuning further.

AAAI Conference 2024 Conference Paper

Make RepVGG Greater Again: A Quantization-Aware Approach

• Xiangxiang Chu
• Liang Li
• Bo Zhang

The tradeoff between performance and inference speed is critical for practical applications. Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly popular ingredient in modern convolutional neural networks. Nonetheless, its quantization performance is usually too poor to deploy (e.g. more than 20% top-1 accuracy drop on ImageNet) when INT8 inference is desired. In this paper, we dive into the underlying mechanism of this failure, where the original design inevitably enlarges quantization error. We propose a simple, robust, and effective remedy to have a quantization-friendly structure that also enjoys reparameterization benefits. Our method greatly bridges the gap between INT8 and FP32 accuracy for RepVGG. Without bells and whistles, the top-1 accuracy drop on ImageNet is reduced within 2% by standard post-training quantization. Extensive experiments on detection and semantic segmentation tasks verify its generalization.

AAAI Conference 2024 Conference Paper

Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models

• Liang Li
• Qingyuan Li
• Bo Zhang
• Xiangxiang Chu

As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization methods, such as GPTQ, have made progress in achieving acceptable 4-bit weight-only quantization, attempts at lower-bit quantization often result in severe performance degradation. In this paper, we introduce a technique called norm tweaking, which can be used as a plugin in current PTQ methods to achieve high precision while being cost-efficient. Our approach is inspired by the observation that rectifying the quantized activation distribution to match its float counterpart can readily restore accuracy for LLMs. To achieve this, we carefully design a tweaking strategy that includes calibration data generation and channel-wise distance constraint to update the weights of normalization layers for better generalization. We conduct extensive experiments on various datasets using several open-sourced LLMs. Our method demonstrates significant improvements in both weight-only quantization and joint quantization of weights and activations, surpassing existing PTQ methods. On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones. Our simple and effective approach makes it more practical for real-world applications.

ICRA Conference 2024 Conference Paper

SAGE-ICP: Semantic Information-Assisted ICP

• Jiaming Cui
• Jiming Chen
• Liang Li

Robust and accurate pose estimation in unknown environments is an essential part of robotic applications. We focus on LiDAR-based point-to-point ICP combined with effective semantic information. This paper proposes a novel semantic information-assisted ICP method named SAGE-ICP, which leverages semantics in odometry. The semantic information for the whole scan is timely and efficiently extracted by a 3D convolution network, and these point-wise labels are deeply involved in every part of the registration, including semantic voxel downsampling, data association, adaptive local map, and dynamic vehicle removal. Unlike previous semantic-aided approaches, the proposed method can improve localization accuracy in large-scale scenes even if the semantic information has certain errors. Experimental evaluations on KITTI and KITTI-360 show that our method outperforms the baseline methods, and improves accuracy while maintaining real-time performance, i. e. , runs faster than the sensor frame rate.

AAAI Conference 2023 Conference Paper

Hard Sample Aware Network for Contrastive Deep Graph Clustering

• Yue Liu
• Xihong Yang
• Sihang Zhou
• Xinwang Liu
• Zhen Wang
• Ke Liang
• Wenxuan Tu
• Liang Li

Contrastive deep graph clustering, which aims to divide nodes into disjoint groups via contrastive mechanisms, is a challenging research spot. Among the recent works, hard sample mining-based algorithms have achieved great attention for their promising performance. However, we find that the existing hard sample mining methods have two problems as follows. 1) In the hardness measurement, the important structural information is overlooked for similarity calculation, degrading the representativeness of the selected hard negative samples. 2) Previous works merely focus on the hard negative sample pairs while neglecting the hard positive sample pairs. Nevertheless, samples within the same cluster but with low similarity should also be carefully learned. To solve the problems, we propose a novel contrastive deep graph clustering method dubbed Hard Sample Aware Network (HSAN) by introducing a comprehensive similarity measure criterion and a general dynamic sample weighing strategy. Concretely, in our algorithm, the similarities between samples are calculated by considering both the attribute embeddings and the structure embeddings, better revealing sample relationships and assisting hardness measurement. Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones. In this way, our method can mine not only the hard negative samples but also the hard positive sample, thus improving the discriminative capability of the samples further. Extensive experiments and analyses demonstrate the superiority and effectiveness of our proposed method. The source code of HSAN is shared at https://github.com/yueliu1999/HSAN and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

AAAI Conference 2023 Conference Paper

Let the Data Choose: Flexible and Diverse Anchor Graph Fusion for Scalable Multi-View Clustering

• Pei Zhang
• Siwei Wang
• Liang Li
• Changwang Zhang
• Xinwang Liu
• En Zhu
• Zhe Liu
• Lu Zhou

In the past few years, numerous multi-view graph clustering algorithms have been proposed to enhance the clustering performance by exploring information from multiple views. Despite the superior performance, the high time and space expenditures limit their scalability. Accordingly, anchor graph learning has been introduced to alleviate the computational complexity. However, existing approaches can be further improved by the following considerations: (i) Existing anchor-based methods share the same number of anchors across views. This strategy violates the diversity and flexibility of multi-view data distribution. (ii) Searching for the optimal anchor number within hyper-parameters takes much extra tuning time, which makes existing methods impractical. (iii) How to flexibly fuse multi-view anchor graphs of diverse sizes has not been well explored in existing literature. To address the above issues, we propose a novel anchor-based method termed Flexible and Diverse Anchor Graph Fusion for Scalable Multi-view Clustering (FDAGF) in this paper. Instead of manually tuning optimal anchor with massive hyper-parameters, we propose to optimize the contribution weights of a group of pre-defined anchor numbers to avoid extra time expenditure among views. Most importantly, we propose a novel hybrid fusion strategy for multi-size anchor graphs with theoretical proof, which allows flexible and diverse anchor graph fusion. Then, an efficient linear optimization algorithm is proposed to solve the resultant problem. Comprehensive experimental results demonstrate the effectiveness and efficiency of our proposed framework. The source code is available at https://github.com/Jeaninezpp/FDAGF.

NeurIPS Conference 2023 Conference Paper

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

• Yutong Kou
• Jin Gao
• Bing Li
• Gang Wang
• Weiming Hu
• Yizheng Wang
• Liang Li

Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size. To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa. This enables us to solve the dilemma of attending to a larger visual field while retaining more raw information for the target despite a smaller input size. Our formulation for the non-uniform resizing can be efficiently solved through quadratic programming (QP) and naturally integrated into most of the crop-based local trackers. Comprehensive experiments on five challenging datasets based on two kinds of transformer trackers, \ie, OSTrack and TransT, demonstrate consistent improvements over them. In particular, applying our method to the speed-oriented version of OSTrack even outperforms its performance-oriented counterpart by 0. 6\% AUC on TNL2K, while running 50\% faster and saving over 55\% MACs. Codes and models are available at https: //github. com/Kou-99/ZoomTrack.

AAAI Conference 2022 Conference Paper

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

• Jiawei Liu
• Zhipeng Huang
• Liang Li
• Kecheng Zheng
• Zheng-Jun Zha

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person reidentification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

NeurIPS Conference 2022 Conference Paper

Leveraging Inter-Layer Dependency for Post -Training Quantization

• changbao wang
• DanDan Zheng
• Yuanliu Liu
• Liang Li

Prior works on Post-training Quantization (PTQ) typically separate a neural network into sub-nets and quantize them sequentially. This process pays little attention to the dependency across the sub-nets, hence is less optimal. In this paper, we propose a novel Network-Wise Quantization (NWQ) approach to fully leveraging inter-layer dependency. NWQ faces a larger scale combinatorial optimization problem of discrete variables than in previous works, which raises two major challenges: over-fitting and discrete optimization problem. NWQ alleviates over-fitting via a Activation Regularization (AR) technique, which better controls the activation distribution. To optimize discrete variables, NWQ introduces Annealing Softmax (ASoftmax) and Annealing Mixup (AMixup) to progressively transition quantized weights and activations from continuity to discretization, respectively. Extensive experiments demonstrate that NWQ outperforms previous state-of-the-art by a large margin: 20. 24\% for the challenging configuration of MobileNetV2 with 2 bits on ImageNet, pushing extremely low-bit PTQ from feasibility to usability. In addition, NWQ is able to achieve competitive results with only 10\% computation cost of previous works.

AAAI Conference 2022 Conference Paper

Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-identification

• Zhipeng Huang
• Jiawei Liu
• Liang Li
• Kecheng Zheng
• Zheng-Jun Zha

RGB-infrared person re-identification is an emerging crossmodality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modalityadaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It formulates modality mixup procedure as Markov decision process, where an actor-critic agent learns dynamical and local linear interpolation policy between different regions of cross-modality images under a deep reinforcement learning framework. Such policy guarantees modality-invariance in a more continuous latent space and avoids manifold intrusion by the corrupted mixed modality samples. Moreover, to further counter modality discrepancy and enforce invariant visual semantics at the feature-level, MID employs modality-adaptive convolution decomposition to disassemble a regular convolution layer into modalityspecific basis layers and a modality-shared coefficient layer. Extensive experimental results on two challenging benchmarks demonstrate superior performance of MID over stateof-the-art methods.

AAAI Conference 2022 Conference Paper

Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency

• Zhenhuan Liu
• Liang Li
• Huajie Jiang
• Xin Jin
• Dandan Tu
• Shuhui Wang
• Zheng-Jun Zha

In recent years, creative content generations like style transfer and neural photo editing have attracted more and more attention. Among these, cartoonization of real-world scenes has promising applications in entertainment and industry. Different from image translations focusing on improving the style effect of generated images, video cartoonization has additional requirements on the temporal consistency. In this paper, we propose a spatially-adaptive semantic alignment framework with perceptual motion consistency for coherent video cartoonization in an unsupervised manner. The semantic alignment module is designed to restore deformation of semantic structure caused by spatial information lost in the encoder-decoder architecture. Furthermore, we devise the spatio-temporal correlative map as a style-independent, global-aware regularization on the perceptual motion consistency. Deriving from similarity measurement of high-level features in photo and cartoon frames, it captures global semantic information beyond raw pixel-value in optical flow. Besides, the similarity measurement disentangles temporal relationships from domain-specific style properties, which helps regularize the temporal consistency without hurting style effects of cartoon images. Qualitative and quantitative experiments demonstrate our method is able to generate highly stylistic and temporal consistent cartoon videos.

JBHI Journal 2021 Journal Article

A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study

• Siwen Wang
• Di Dong
• Liang Li
• Hailin Li
• Yan Bai
• Yahua Hu
• Yuanyi Huang
• Xiangrong Yu

Objective: Coronavirus disease 2019 (COVID-19) has caused considerable morbidity and mortality, especially in patients with underlying health conditions. A precise prognostic tool to identify poor outcomes among such cases is desperately needed. Methods: Total 400 COVID-19 patients with underlying health conditions were retrospectively recruited from 4 centers, including 54 dead cases (labeled as poor outcomes) and 346 patients discharged or hospitalized for at least 7 days since initial CT scan. Patients were allocated to a training set (n = 271), a test set (n = 68), and an external test set (n = 61). We proposed an initial CT-derived hybrid model by combining a 3D-ResNet10 based deep learning model and a quantitative 3D radiomics model to predict the probability of COVID-19 patients reaching poor outcome. The model performance was assessed by area under the receiver operating characteristic curve (AUC), survival analysis, and subgroup analysis. Results: The hybrid model achieved AUCs of 0. 876 (95% confidence interval: 0. 752-0. 999) and 0. 864 (0. 766-0. 962) in test and external test sets, outperforming other models. The survival analysis verified the hybrid model as a significant risk factor for mortality (hazard ratio, 2. 049 [1. 462–2. 871], P P Conclusion: The hybrid model that combined deep learning and radiomics could accurately identify poor outcomes in COVID-19 patients with underlying health conditions from initial CT scans. The great risk stratification ability could help alert risk of death and allow for timely surveillance plans.

AAAI Conference 2021 Conference Paper

Forecasting Reservoir Inflow via Recurrent Neural ODEs

• Fan Zhou
• Liang Li

Forecasting reservoir inflow is critical for making many policies, ranging from flood control and agriculture irrigation to water ecology management, hydropower generation, and landslide prevention. Prior studies mainly exploit autoregressive models – e. g. , recurrent neural networks (RNN) and its many variants – to model the flow time series’s temporal pattern. However, existing approaches rely on regular and accurate inflow observations, which either fail to predict multiscale inflow (e. g. , an hour, a day, or a month ahead prediction) or ignore the uncertainty of observations due to confounding factors such as snowmelt and precipitation. To address the limitations, we propose a novel inflow forecasting model by incorporating the uncertainty of the observations into the RNN model and the continuous-time dynamics of the latent states with neural ordinary differential equations (ODE). Our method, called FlowODE, explicitly encodes the stochasticity of hidden conditions in addition to the temporal dependencies among inflow observations. Moreover, FlowODE explores a continuum of layers instead of discrete RNNs to model the hidden states’ dynamics, allowing us to infer the inflow at any time horizon flexibly. We conduct extensive experiments on the real-world datasets collected from two largescale hydropower dams. The results show that our method consistently outperforms previous inflow forecasting models while providing adaptable predictions and a flexible balance between prediction accuracy and computational cost.

JBHI Journal 2021 Journal Article

Joint Extraction of Retinal Vessels and Centerlines Based on Deep Semantics and Multi-Scaled Cross-Task Aggregation

• Rui Xu
• Tiantian Liu
• Xinchen Ye
• Fei Liu
• Lin Lin
• Liang Li
• Satoshi Tanaka
• Yen-Wei Chen

Retinal vessel segmentation and centerline extraction are crucial steps in building a computer-aided diagnosis system on retinal images. Previous works treat them as two isolated tasks, while ignoring their tight association. In this paper, we propose a deep semantics and multi-scaled cross-task aggregation network that takes advantage of the association to jointly improve their performances. Our network is featured by two sub-networks. The forepart is a deep semantics aggregation sub-network that aggregates strong semantic information to produce more powerful features for both tasks, and the tail is a multi-scaled cross-task aggregation sub-network that explores complementary information to refine the results. We evaluate the proposed method on three public databases, which are DRIVE, STARE and CHASE_DB1. Experimental results show that our method can not only simultaneously extract retinal vessels and their centerlines but also achieve the state-of-the-art performances on both tasks.

AAAI Conference 2021 Conference Paper

Symbolic Music Generation with Transformer-GANs

• Aashiq Muhamed
• Liang Li
• Xingjian Shi
• Suri Yaddanapudi
• Wayne Chi
• Dylan Jackson
• Rahul Suresh
• Zachary C. Lipton

Autoregressive models using Transformers have emerged as the dominant approach for music generation with the goal of synthesizing minute-long compositions that exhibit largescale musical structure. These models are commonly trained by minimizing the negative log-likelihood (NLL) of the observed sequence in an autoregressive manner. Unfortunately, the quality of samples from these models tends to degrade significantly for long sequences, a phenomenon attributed to exposure bias. Fortunately, we are able to detect these failures with classifiers trained to distinguish between real and sampled sequences, an observation that motivates our exploration of adversarial losses to complement the NLL objective. We use a pre-trained Span-BERT model for the discriminator of the GAN, which in our experiments helped with training stability. We use the Gumbel-Softmax trick to obtain a differentiable approximation of the sampling process. This makes discrete sequences amenable to optimization in GANs. In addition, we break the sequences into smaller chunks to ensure that we stay within a given memory budget. We demonstrate via human evaluations and a new discriminative metric that the music generated by our approach outperforms a baseline trained with likelihood maximization, the state-of-the-art Music Transformer, and other GANs used for sequence generation. 57% of people prefer music generated via our approach while 43% prefer Music Transformer.

UAI Conference 2021 Conference Paper

TreeBERT: A tree-based pre-trained model for programming language

• Xue Jiang
• Zhuoran Zheng
• Chen Lyu 0001
• Liang Li
• Lei Lyu 0001

Source code can be parsed into the abstract syntax tree (AST) based on defined syntax rules. However, in pre-training, little work has considered the incorporation of tree structure into the learning process. In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks. To utilize tree structure, TreeBERT represents the AST corresponding to the code as a set of composition paths and introduces node position embedding. The model is trained by tree masked language modeling (TMLM) and node order prediction (NOP) with a hybrid objective. TMLM uses a novel masking strategy designed according to the tree’s characteristics to help the model understand the AST and infer the missing semantics of the AST. With NOP, TreeBERT extracts the syntactical structure by learning the order constraints of nodes in AST. We pre-trained TreeBERT on datasets covering multiple programming languages. On code summarization and code documentation tasks, TreeBERT outperforms other pre-trained models and state-of-the-art models designed for these tasks. Furthermore, TreeBERT performs well when transferred to the pre-trained unseen programming language.

JBHI Journal 2020 Journal Article

A Deep Learning Prognosis Model Help Alert for COVID-19 Patients at High-Risk of Death: A Multi-Center Study

• Lingwei Meng
• Di Dong
• Liang Li
• Meng Niu
• Yan Bai
• Meiyun Wang
• Xiaoming Qiu
• Yunfei Zha

Since its outbreak in December 2019, the persistent coronavirus disease (COVID-19) became a global health emergency. It is imperative to develop a prognostic tool to identify high-risk patients and assist in the formulation of treatment plans. We retrospectively collected 366 severe or critical COVID-19 patients from four centers, including 70 patients who died within 14 days (labeled as high-risk patients) since their initial CT scan and 296 who survived more than 14 days or were cured (labeled as low-risk patients). We developed a 3D densely connected convolutional neural network (termed De-COVID19-Net) to predict the probability of COVID-19 patients belonging to the high-risk or low-risk group, combining CT and clinical information. The area under the curve (AUC) and other evaluation techniques were used to assess our model. The De-COVID19-Net yielded an AUC of 0. 952 (95% confidence interval, 0. 928-0. 977) on the training set and 0. 943 (0. 904-0. 981) on the test set. The stratified analyses indicated that our model's performance is independent of age, sex, and with/without chronic diseases. The Kaplan-Meier analysis revealed that our model could significantly categorize patients into high-risk and low-risk groups ( p < 0. 001). In conclusion, De-COVID19-Net can non-invasively predict whether a patient will die shortly based on the patient's initial CT scan with an impressive performance, which indicated that it could be used as a potential prognosis tool to alert high-risk patients and intervene in advance.

IJCAI Conference 2020 Conference Paper

A Structured Latent Variable Recurrent Network With Stochastic Attention For Generating Weibo Comments

• Shijie Yang
• Liang Li
• Shuhui Wang
• Weigang Zhang
• Qingming Huang
• Qi Tian

Building intelligent agents to generate realistic Weibo comments is challenging. For such realistic Weibo comments, the key criterion is improving diversity while maintaining coherency. Considering that the variability of linguistic comments arises from multi-level sources, including both discourse-level properties and word-level selections, we improve the comment diversity by leveraging such inherent hierarchy. In this paper, we propose a structured latent variable recurrent network, which exploits the hierarchical-structured latent variables with stochastic attention to model the variations of comments. First, we endow both discourse-level and word-level latent variables with hierarchical and temporal dependencies for constructing multi-level hierarchy. Second, we introduce a stochastic attention to infer the key-words of interest in the input post. As a result, diverse comments can be generated with both discourse-level properties and local-word selections. Experiments on open-domain Weibo data show that our model generates more diverse and realistic comments.

JBHI Journal 2020 Journal Article

Classification of Severe and Critical Covid-19 Using Deep Learning and Radiomics

• Cong Li
• Di Dong
• Liang Li
• Wei Gong
• Xiaohu Li
• Yan Bai
• Meiyun Wang
• Zhenhua Hu

Objective: The coronavirus disease 2019 (COVID-19) is rapidly spreading inside China and internationally. We aimed to construct a model integrating information from radiomics and deep learning (DL) features to discriminate critical cases from severe cases of COVID-19 using computed tomography (CT) images. Methods: We retrospectively enrolled 217 patients from three centers in China, including 82 patients with severe disease and 135 with critical disease. Patients were randomly divided into a training cohort (n = 174) and a test cohort (n = 43). We extracted 102 3-dimensional radiomic features from automatically segmented lung volume and selected the significant features. We also developed a 3-dimensional DL network based on center-cropped slices. Using multivariable logistic regression, we then created a merged model based on significant radiomic features and DL scores. We employed the area under the receiver operating characteristic curve (AUC) to evaluate the model's performance. We then conducted cross validation, stratified analysis, survival analysis, and decision curve analysis to evaluate the robustness of our method. Results: The merged model can distinguish critical patients with AUCs of 0. 909 (95% confidence interval [CI]: 0. 859–0. 952) and 0. 861 (95% CI: 0. 753–0. 968) in the training and test cohorts, respectively. Stratified analysis indicated that our model was not affected by sex, age, or chronic disease. Moreover, the results of the merged model showed a strong correlation with patient outcomes. Significance: A model combining radiomic and DL features of the lung could help distinguish critical cases from severe cases of COVID-19.

IJCAI Conference 2020 Conference Paper

Enhancing Urban Flow Maps via Neural ODEs

• Fan Zhou
• Liang Li
• Ting Zhong
• Goce Trajcevski
• Kunpeng Zhang
• Jiahao Wang

Flow super-resolution (FSR) enables inferring fine-grained urban flows with coarse-grained observations and plays an important role in traffic monitoring and prediction. The existing FSR solutions rely on deep CNN models (e. g. , ResNet) for learning spatial correlation, incurring excessive memory cost and numerous parameter updates. We propose to tackle the urban flows inference using dynamic systems paradigm and present a new method FODE -- FSR with Ordinary Differential Equations (ODEs). FODE extends neural ODEs by introducing an affine coupling layer to overcome the problem of numerically unstable gradient computation, which allows more accurate and efficient spatial correlation estimation, without extra memory cost. In addition, FODE provides a flexible balance between flow inference accuracy and computational efficiency. A FODE-based augmented normalization mechanism is further introduced to constrain the flow distribution with the influence of external factors. Experimental evaluations on two real-world datasets demonstrate that FODE significantly outperforms several baseline approaches.

AAAI Conference 2020 Conference Paper

Meta-Learning PAC-Bayes Priors in Model Averaging

• Yimin Huang
• Weiran Huang
• Liang Li
• Zhenguo Li

Nowadays model uncertainty has become one of the most important problems in both academia and industry. In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model’s uncertainty in order to improve reliability and accuracy of inferences. Here one main challenge is to learn the prior over the model set. To tackle this problem, we propose two data-based algorithms to get proper priors for model averaging. One is for meta-learner, the analysts should use historical similar tasks to extract the information about the prior. The other one is for base-learner, a subsampling method is used to deal with the data step by step. Theoretically, an upper bound of risk for our algorithm is presented to guarantee the performance of the worst situation. In practice, both methods perform well in simulations and real data studies, especially with poor quality data.

ECAI Conference 2020 Conference Paper

Secure Social Recommendation Based on Secret Sharing

• Chaochao Chen 0001
• Liang Li
• Bingzhe Wu
• Cheng Hong 0001
• Li Wang 0056
• Jun Zhou 0011

Nowadays, privacy preserving machine learning has been drawing much attention in both industry and academy. Meanwhile, recommender systems have been extensively adopted by many commercial platforms (e. g. Amazon) and they are mainly built based on user-item interactions. Besides, social platforms (e. g. Facebook) have rich resources of user social information. It is well known that social information, which is rich on social platforms such as Facebook, are useful to build intelligent recommender systems. It is anticipated to combine the social information with the user-item ratings to improve the overall recommendation performance. Most existing recommendation models are built based on the assumptions that the social information are available. However, different platforms are usually reluctant to (or can not) share their data due to certain concerns. In this paper, we first propose a SEcure SOcial RECommendation (SeSoRec) framework which is able to (1) collaboratively mine knowledge from social platform to improve the recommendation performance of the rating platform, and (2) securely keep the raw data of both platforms. We then propose a Secret Sharing based Matrix Multiplication (SSMM) protocol to optimize SeSoRec and prove its correctness and security theoretically. By applying minibatch gradient descent, SeSoRec has linear time complexities in terms of both computation and communication. The comprehensive experimental results on three real-world datasets demonstrate the effectiveness of our proposed SeSoRec and SSMM.

AAAI Conference 2020 Conference Paper

Simultaneous Learning of Pivots and Representations for Cross-Domain Sentiment Classification

• Liang Li
• Weirui Ye
• Mingsheng Long
• Yateng Tang
• Jin Xu
• Jianmin Wang

Cross-domain sentiment classification aims to leverage useful knowledge from a source domain to mitigate the supervision sparsity in a target domain. A series of approaches depend on the pivot features that behave similarly for polarity prediction in both domains. However, the engineering of such pivot features remains cumbersome and prevents us from learning the disentangled and transferable representations from rich semantic and syntactic information. Towards learning the pivots and representations simultaneously, we propose a new Transferable Pivot Transformer (TPT). Our model consists of two networks: a Pivot Selector that learns to detect transferable ngram pivots from contexts, and a Transferable Transformer that learns to generate domain-invariant representations by modeling the correlation between pivot and non-pivot words. The Pivot Selector and Transferable Transformer are jointly optimized through end-to-end back-propagation. We experiment with real tasks of cross-domain sentiment classification over 20 domain pairs where our model outperforms prior arts.

AAAI Conference 2019 Conference Paper

Transferable Attention for Domain Adaptation

• Ximei Wang
• Liang Li
• Weirui Ye
• Mingsheng Long
• Jianmin Wang

Recent work in domain adaptation bridges different domains by adversarially learning a domain-invariant representation that cannot be distinguished by a domain discriminator. Existing methods of adversarial domain adaptation mainly align the global images across the source and target domains. However, it is obvious that not all regions of an image are transferable, while forcefully aligning the untransferable regions may lead to negative transfer. Furthermore, some of the images are significantly dissimilar across domains, resulting in weak image-level transferability. To this end, we present Transferable Attention for Domain Adaptation (TADA), focusing our adaptation model on transferable regions or images. We implement two types of complementary transferable attention: transferable local attention generated by multiple region-level domain discriminators to highlight transferable regions, and transferable global attention generated by single image-level domain discriminator to highlight transferable images. Extensive experiments validate that our proposed models exceed state of the art results on standard domain adaptation datasets.

IJCAI Conference 2018 Conference Paper

Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications

• Weiran Huang
• Jungseul Ok
• Liang Li
• Wei Chen

We study the Combinatorial Pure Exploration problem with Continuous and Separable reward functions (CPE-CS) in the stochastic multi-armed bandit setting. In a CPE-CS instance, we are given several stochastic arms with unknown distributions, as well as a collection of possible decisions. Each decision has a reward according to the distributions of arms. The goal is to identify the decision with the maximum reward, using as few arm samples as possible. The problem generalizes the combinatorial pure exploration problem with linear rewards, which has attracted significant attention in recent years. In this paper, we propose an adaptive learning algorithm for the CPE-CS problem, and analyze its sample complexity. In particular, we introduce a new hardness measure called the consistent optimality hardness, and give both the upper and lower bounds of sample complexity. Moreover, we give examples to demonstrate that our solution has the capacity to deal with non-linear reward functions.

IJCAI Conference 2017 Conference Paper

Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition

• Xinge Zhu
• Liang Li
• Weigang Zhang
• Tianrong Rao
• Min Xu
• Qingming Huang
• Dong Xu

Visual emotion recognition aims to associate images with appropriate emotions. There are different visual stimuli that can affect human emotion from low-level to high-level, such as color, texture, part, object, etc. However, most existing methods treat different levels of features as independent entity without having effective method for feature fusion. In this paper, we propose a unified CNN-RNN model to predict the emotion based on the fused features from different levels by exploiting the dependency among them. Our proposed architecture leverages convolutional neural network (CNN) with multiple layers to extract different levels of features with in a multi-task learning framework, in which two related loss functions are introduced to learn the feature representation. Considering the dependencies within the low-level and high-level features, a new bidirectional recurrent neural network (RNN) is proposed to integrate the learned features from different layers in the CNN model. Extensive experiments on both Internet images and art photo datasets demonstrate that our method outperforms the state-of-the-art methods with at least 7% performance improvement.

IROS Conference 2017 Conference Paper

Human-inspired compliant strategy for peg-in-hole assembly using environmental constraint and coarse force information

• Xiaoqing Li
• Rui Li 0077
• Hong Qiao
• Chao Ma 0011
• Liang Li

Automated assembly, especially peg-in-hole insertion, is a common task in manufacturing. In particular, the high-precision assembly is achieved by high-precision manipulator and sensing system. However, uncertainty and various parts for assembly are still challenges for robotic assembly, especially for low-precision robot and sensors. It is noteworthy that human can implement assembly tasks although the precision of the arm and hand is not comparable with a common industrial robot, in which process compliance is the key characteristic of their motion. In this paper, we present a human-inspired compliant strategy for peg-in-hole assembly task using the environmental constraint and coarse force information. In the proposed strategy, a constraint region is designed for motion planning and utilized for eliminating the uncertainty of the initial positioning error of the peg. Force sensor is applied to sense the contact force of which the direction is used to adjust the movement of the peg. Therefore, high-precision sensor is not necessarily required. Inspired by human compliant assembly, a from coarse to fine adjustment strategy is executed. The contribution of our strategy is that high precision assembly task can be solved by low precision system. The constraint region and force guided directional adjustment have increased the robustness of the system. The strategy is carried out in simulation for round peg-in-hole assembly task. The experimental results show that the assembly task can be successfully completed and demonstrate the effectiveness of our strategy.

AAAI Conference 2017 Conference Paper

Partitioned Sampling of Public Opinions Based on Their Social Dynamics

• Weiran Huang
• Liang Li
• Wei Chen

Public opinion polling is usually done by random sampling from the entire population, treating individual opinions as independent. In the real world, individuals’ opinions are often correlated, e. g. , among friends in a social network. In this paper, we explore the idea of partitioned sampling, which partitions individuals with high opinion similarities into groups and then samples every group separately to obtain an accurate estimate of the population opinion. We rigorously formulate the above idea as an optimization problem. We then show that the simple partitions which contain only one sample in each group are always better, and reduce finding the optimal simple partition to a well-studied Min-r-Partition problem. We adapt an approximation algorithm and a heuristic to solve the optimization problem. Moreover, to obtain opinion similarity efficiently, we adapt a well-known opinion evolution model to characterize social interactions, and provide an exact computation of opinion similarities based on the model. We use both synthetic and real-world datasets to demonstrate that the partitioned sampling method results in significant improvement in sampling quality and it is robust when some opinion similarities are inaccurate or even missing.

FOCS Conference 2017 Conference Paper

Variable-Version Lovász Local Lemma: Beyond Shearer's Bound

• Kun He 0011
• Liang Li
• Xingwu Liu
• Yuyi Wang 0001
• Mingji Xia

A tight criterion under which the abstract version Lovász Local Lemma (abstract-LLL) holds was given by Shearer [41] decades ago. However, little is known about that of the variable version LLL (variable-LLL) where events are generated by independent random variables, though variable- LLL naturally models and is enough for almost all applications of LLL. We introduce a necessary and sufficient criterion for variable-LLL, in terms of the probabilities of the events and the event-variable graph specifying the dependency among the events. Based on this new criterion, we obtain boundaries for two families of event-variable graphs, namely, cyclic and treelike bigraphs. These are the first two non-trivial cases where the variable-LLL boundary is fully determined. As a byproduct, we also provide a universal constructive method to find a set of events whose union has the maximum probability, given the probability vector and the event-variable graph. Though it is #P-hard in general to determine variable- LLL boundaries, we can to some extent decide whether a gap exists between a variable-LLL boundary and the corresponding abstract-LLL boundary. In particular, we show that the gap existence can be decided without solving Shearer’s conditions or checking our variable-LLL criterion. Equipped with this powerful theorem, we show that there is no gap if the base graph of the event-variable graph is a tree, while gap appears if the base graph has an induced cycle of length at least 4. The problem is almost completely solved except when the base graph has only 3-cliques, in which case we also get partial solutions. A set of reduction rules are established that facilitate to infer gap existence of a event-variable graph from known ones. As an application, various event-variable graphs, in particular combinatorial ones, are shown to be gapful/gapless.

SODA Conference 2013 Conference Paper

Correlation Decay up to Uniqueness in Spin Systems

• Liang Li
• Pinyan Lu
• Yitong Yin

We give a complete characterization of the two-state anti-ferromagnetic spin systems which exhibit strong spatial mixing on general graphs. We show that a two-state anti-ferromagnetic spin system exhibits strong spatial mixing on all graphs of maximum degree at most Δ if and only if the system has a unique Gibbs measure on infinite regular trees of degree up to Δ, where Δ can be either bounded or unbounded. As a consequence, there exists an FPTAS for the partition function of a two-state anti-ferromagnetic spin system on graphs of maximum degree at most Δ when the uniqueness condition is satisfied on infinite regular trees of degree up to Δ. In particular, an FPTAS exists for arbitrary graphs if the uniqueness is satisfied on all infinite regular trees. This covers as special cases all previous algorithmic results for two-state anti-ferromagnetic systems on general-structure graphs. Combining with the FPRAS for two-state ferromagnetic spin systems of Jerrum-Sinclair and Goldberg-Jerrum-Paterson, and the very recent hardness results of Sly-Sun and independently of Galanis-Štefankovič-Vigoda, this gives a complete classification, except at the phase transition boundary, of the approximability of all two-state spin systems, on either degree-bounded families of graphs or family of all graphs.

SODA Conference 2012 Conference Paper

Approximate counting via correlation decay in spin systems

• Liang Li
• Pinyan Lu
• Yitong Yin