Arrow Research search

Author name cluster

Haotian Wang

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.

27 papers
2 author rows

Possible papers

27

EAAI Journal 2026 Journal Article

A hybrid deep learning model for energy consumption prediction in hot die forging production lines

  • Zhenhua Wang
  • Haotian Wang
  • Chenheng Yuan
  • Wangzhe Du
  • Yuanming Liu

The energy consumption of hot die forging production lines is influenced by multi-process flows, multi-equipment collaboration, and rapidly changing operating conditions, exhibiting strong nonlinearity, spatiotemporal coupling, and fluctuation. Together with the full-process transfer of workpieces across heating, forming, and handling stages, these factors make accurate energy prediction challenging. To address this issue, whole-process time series data from an automotive hot die forging line are used to construct an input sequence integrating process parameters, equipment states, and scheduling information. Based on this, a multi-branch hybrid prediction model, Convolutional Neural Network-Temporal Convolutional Network-Dynamic Gated Bidirectional Long Short-Term Memory-Transformer (CTDG-BiLSTM-Transformer), is proposed. The model adopts a Convolutional Neural Network (CNN)-Temporal Convolutional Network (TCN) dual-path structure to extract multi-scale spatiotemporal features, employs a Cross-Modal Attention (CMA) mechanism for dynamic feature weighting, and combines Dynamic Gated Bidirectional Long Short-Term Memory (DG-BiLSTM) with a Transformer encoder to capture complex sequential dependencies. Experimental results show that the proposed model outperforms Multiple Linear Regression (MLR), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), and as well as Long Short-Term Memory (LSTM), achieving a Root Mean Square Error (RMSE) of 4. 901, Mean Absolute Error (MAE) of 2. 049, Mean Absolute Percentage Error (MAPE) of 58. 15%, and Coefficient of Determination (R2) of 0. 9821. Ablation studies further confirm the effectiveness and complementarity of each component, demonstrating its potential for forging energy modeling and intelligent optimization.

Details DOI

AAAI Conference 2026 Conference Paper

AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models

  • Lian Yan
  • Haotian Wang
  • Chen Tang
  • Haifeng Liu
  • Tianyang Sun
  • Liangliang Liu
  • Yi Guan
  • Jingchi Jiang

n the agricultural domain, the deployment of large language models (LLMs) is hindered by the lack of training data and evaluation benchmarks. To mitigate this issue, we propose AgriEval, the first comprehensive Chinese agricultural benchmark with three main characteristics: (1) Comprehensive Capability Evaluation. AgriEval covers six major agriculture categories and 29 subcategories within agriculture, addressing four core cognitive scenarios—memorization, understanding, inference, and generation. (2) High-Quality Data. The dataset is curated from university-level examinations and assignments, providing a natural and robust benchmark for assessing the capacity of LLMs to apply knowledge and make expert-like decisions. (3) Diverse Formats and Extensive Scale. AgriEval comprises 14,697 multiple-choice questions and 2,167 open-ended question-and-answer questions, establishing it as the most extensive agricultural benchmark available to date. We also present comprehensive experimental results over 51 open-source and commercial LLMs. The experimental results reveal that most existing LLMs struggle to achieve 60 percent accuracy, underscoring the developmental potential in agricultural LLMs. Additionally, we conduct extensive experiments to investigate factors influencing model performance and propose strategies for enhancement.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Attention to Threat-Relevant Objects: Reasoning Detection in Autonomous Driving via Multimodal Large Language Models

  • Yulin He
  • Wei Chen
  • Xinbiao Gan
  • Siqi Wang
  • Haotian Wang
  • Yusong Tan

Perceiving threats is an innate human instinct. During driving, humans naturally focus their attention on objects that pose real potential risks. Motivated by this observation, we shift the focus from traditional class-based detection to a novel task termed threat-oriented reasoning detection in autonomous driving. This task aims to localize threat objects and reason about their threat levels from a driver-centric perspective. To support this task, we build a benchmark comprising diverse corner-case scenarios, annotated by multiple experienced drivers to reflect human-aligned threat cognition. Given the reasoning demands of this task, we then explore the capabilities of multi-modal large language models (MLLMs) and introduce two methods based on whether the MLLM supports object detection: 1) For MLLMs lacking detection capability, we introduce ThreatCoT, a plug-and-play training-free method that combines chain-of-thought (CoT) with a visual expert toolchain to support step-by-step reasoning. 2) For MLLMs with detection support, we introduce ThreatReasoner, an end-to-end reinforcement learning (RL)-based method built on the GRPO algorithm, which enables per-object reasoning through a fully unsupervised reward strategy. Both quantitative and qualitative experiments show that our methods can effectively unlock the new capabilities of MLLM in threat-oriented reasoning detection.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Causally-Aware Attribute Completion for Incomplete Federated Graph Clustering

  • Jingxin Liu
  • Wenxuan Tu
  • Haotian Wang
  • Renda Han
  • Haoyi Li
  • Junlong Wu
  • Xiangyan Tang

Node-level federated graph clustering allows multiple unlabeled subgraph holders to collaboratively train on node-level tasks without sharing private information. Existing methods usually assume that the node attributes are complete and have achieved promising progress. However, in the Federated Graph Learning (FGL) scenarios, this assumption is overly strict due to failures in data collection devices. Consequently, most existing FGL frameworks struggle to extract useful features from attribute-incomplete graphs for clustering, yet the issue remains underexplored. To bridge this gap, we propose a causally-aware attribute completion for Incomplete Federated Graph Clustering (IFedGC), which constructs a reliable global causal structure that incorporates clustering-friendly information to guide attribute completion for each subgraph. Specifically, in the attribute completion step, we first construct the causal structure to extract the causal relationships between initialized features, and then upload them to the server. Subsequently, we integrate multiple uploaded causal structures into a global causal one to achieve cross-client attribute completion. Moreover, to support reliable clustering, we first collect the high-confidence cluster centroids from each subgraph using a Graph Neural Network (GNN) model and subsequently aggregate these centroids on the server. The above two steps are seamlessly integrated into a unified FGL framework to obtain a clustering-oriented causal structure, which is sent back to the client to promote high-quality attribute completion for better clustering. Extensive results on five benchmark datasets demonstrate the effectiveness and superiority of IFedGC against its competitors.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Detecting Unobserved Confounders: A Kernelized Regression Approach

  • Yikai Chen
  • Yunxin Mao
  • Chunyuan Zheng
  • Hao Zou
  • Shanzhi Gu
  • Shixuan Liu
  • Yang Shi
  • Wenjing Yang

Detecting unobserved confounders is crucial for reliable causal inference in observational studies. Existing methods require either linearity assumptions or multiple heterogeneous environments, limiting applicability to nonlinear single-environment settings. To bridge this gap, we propose Kernel Regression Confounder Detection (KRCD), a novel method for detecting unobserved confounding in nonlinear observational data under single-environment conditions. KRCD leverages reproducing kernel Hilbert spaces to model complex dependencies. By comparing standard and higher-order kernel regressions, we derive a test statistic whose significant deviation from zero indicates unobserved confounding. Theoretically, we prove two key results: First, in infinite samples, regression coefficients coincide if and only if no unobserved confounders exist. Second, finite-sample differences converge to zero-mean Gaussian distributions with tractable variance. Extensive experiments on synthetic benchmarks and the Twins dataset demonstrate that KRCD not only outperforms existing baselines but also achieves superior computational efficiency.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning

  • Mingyang Geng
  • Shanzhi Gu
  • Zhipeng Liu
  • Chuanfu Xu
  • Zhaoyang Qu
  • Haotian Wang

Recent advances in multi-agent Large Language Model-based code generation enable collaborative software development through role-specialized agents. However, failure localization of code generation remains challenging due to inter-agent dependencies and solution-path multiplicity. Consequently, existing prompting-based localization methods exhibit vulnerability towards semantically valid but non-canonical strategies. To address this, we propose FLKR (Failure Localization via Knowledge-guided Reasoning), an self-supervised framework that combines behavior encoding, knowledge-strategy alignment, and consistency scoring for solution-path invariant localization. To evaluate, we also introduce COFL (Code Oriented Failure Localization), the first expert-annotated benchmark for fine-grained failure localization. Experiments show FLKR outperforms state-of-the-art prompting-based baselines by up to 14 points in Fault Localization Accuracy and 45 points in Top-1 accuracy, with strong performance in divergent, real-world, and refinement-critical cases. Such results demonstrate that our proposed FLKR generalizes well to real-world software development scenarios and opens up a new direction for failure-aware refinement recommendation by providing precise and interpretable responsibility signals.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Federated Graph-level Clustering Network with Attribute Inference

  • Renda Han
  • Junlong Wu
  • Wenxuan Tu
  • Jingxin Liu
  • Haotian Wang
  • Jieren Cheng

With the rise of vertical segmentation in real-world data, federated graph-level clustering has gained significant attention in recent years. However, the inherent missing attributes in graph datasets held by certain clients lead to suboptimal local parameter updates and misaligned global parameter consensus. This results in knowledge shifts during negotiation to ultimately impair overall clustering performance. This issue remains largely underexplored in the current advanced research. To bridge this gap, we propose a novel deep learning network called Federated Graph-level Clustering Network with Attribute Inference (FedAI), which utilizes high-confidence prior knowledge from each domain and multi-party collaborative optimization to achieve efficient reasoning of unknown features. Specifically, on the client, high-confidence graph samples are projected into a latent space. We then extract and upload irreversible path digest information and attribute-oriented inference signals from them. On the server, we first identify affinity relationships hierarchically via the improved graph kernel method. We then infer the features of clients lacking node attributes through a prior structure-guide recovery operator, facilitating inter-client knowledge transfer for better clustering. Experimental results on 15 cross-dataset and cross-domain non-IID graph datasets demonstrate that FedAI consistently outperforms existing methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Make Model Transparent: Brain Network Analysis via Causal and Knowledge Graph Learning

  • Lingyuan Meng
  • Ke Liang
  • Hao Yu
  • Haotian Wang
  • Miaomiao Li
  • Xinwang Liu

Brain network analysis technology reveals the organizational mechanism and information processing mode by constructing the structural connection network between brain regions. It has achieved satisfactory results in brain disease prediction tasks, promoting the progress of neuroscience. In recent years, graph transformer has become the most mainstream method for brain analysis with its powerful feature extraction ability and attention mechanism. However, these methods face two challenges, i.e., lack of interpretability, and neglect of semantic associations among brain regions. To solve these problems, we proposed a large language model (LLM)-driven causal knowledge brain network transformer framework, termed BrainCKT, which is plug-and-play, and can adapt to most of the existing mainstream graph transformer-based methods. Specifically, we constructed a brain region causal graph and used its adjacency matrix to guide the learning process of the self-attention mechanism. In addition, we constructed a brain science knowledge graph and encoded it through a pre-trained model to enhance the original brain region features. Finally, we integrated BrainCKT into four mainstream graph transformer baselines for verification. Experimental results on two brain imaging datasets proved the effectiveness of BrainCKT.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic Agents

  • Xinpeng Lv
  • Chunyuan Zheng
  • Yunxin Mao
  • Renzhe Xu
  • Hao Zou
  • Shanzhi Gu
  • Liyang Xu
  • Huan Chen

Strategic machine learning investigates scenarios where agents manipulate their features to receive favorable decisions from predictive models. To address fairness concerns intrinsic to strategic classification, recent work has introduced group-specific fairness constraints. However, current fairness-aware approaches face a fundamental dilemma in the issue of fairness exposure: making these constraints public enables strategic manipulation and can lead to fairness reversal, while keeping them hidden may reduce social welfare and discourage genuine improvement. To fill this gap, we subsequently propose the problem of Partial Fairness Awareness (PFA), as our theoretical analysis informs that such a dilemma can be mitigated by releasing the candidate set of fairness constraints and concealing the grounding constraint. To be specific, we introduce a belief-guided strategic mechanism wherein agents iteratively interact with the decision system and maintain a belief distribution over the candidate set of fairness constraints. This belief-guided process enables agents, through iterative interaction and feedback, to update their belief distribution over the candidate set, thereby gradually aligning their belief with the grounding fairness constraint employed by the system. Extensive experiments on real-world and synthetic datasets demonstrate that PFA achieves lower group fairness gaps, higher acceptance of truly qualified individuals, and more stable outcomes compared to fully public or private fairness regimes.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Personalized Federated Graph-Level Clustering Network

  • Jingxin Liu
  • Wenxuan Tu
  • Renda Han
  • Junlong Wu
  • Haotian Wang
  • Guohui Liu
  • Xiangyan Tang
  • Yue Yang

In the federated clustering task, structural heterogeneity across clients inevitably impedes effective multi-source information sharing. To solve this issue, Personalized Federated Learning (PFL) has emerged as a potentially effective solution for image and text clustering. Unlike Euclidean data, graph-structured data exhibits diverse and fragile local patterns, which widely exist in real-world scenarios. Multi-graph data analysis in the federated learning setting is challenging and important, yet remains underexplored. This motivates us to propose a novel PERsonalized Federated graph-lEvel Clustering neTwork (PERFECT), which generates a specialized aggregation strategy for each client by uploading key model parameters and representative samples without sharing private information. Specifically, for each client, we first reconstruct privacy-preserving representative samples in a min-max optimization manner and then upload these samples to the server for subsequent personalized parameter aggregation. On the server, we first extract graph-level embeddings from the uploaded data, and then estimate affinities among multiple learned embeddings to formulate a personalized aggregation strategy for each client. Subsequently, to help each local model better identify the cluster boundaries, we utilize clustering-wise gradient to update the key components in the personalized model parameters from the server. Extensive experimental results have demonstrated the effectiveness and superiority of PERFECT over its competitors.

PDF Details DOI

AAAI Conference 2026 Conference Paper

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

  • Haotian Wang
  • Yuzhe Weng
  • Jun Du
  • Haoran Xu
  • Xiaoyan Wu
  • Shan He
  • Bing Yin
  • Cong Liu

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Towards Robust Event-Based Depth Estimation: Bridging Synthetic and Real Domains with Motion Adaptation

  • Yuzhe Ji
  • Haotian Wang
  • Yijie Chen
  • Xiang Cheng
  • Liuqing Yang
  • Xinhu Zheng

Event cameras provide microsecond latency and high dynamic range, making them ideal for 3D perception tasks in traffic scenes with challenging lighting conditions. Yet existing methods often struggle to generalize to out-of-domain environments due to the limited availability of diverse training data. While synthetic data offers an easily accessible alternative, it introduces a significant sim-to-real gap, particularly in motion patterns. We tackle this challenge by introducing Motion-Adaptation Mamba (MA-Mamba), a dual-track framework that advances both architecture and data augmentation. At the architectural level, we introduce a lightweight Spatio-Temporal Association module that captures motion-induced appearance variations at arbitrary scales, and an Adaptive Memory Balancing module, built on the Mamba state-space framework, that adaptively filters memory updates to maintain stable scene context under diverse dynamics. At the data level, we design event-oriented augmentations that simulate varied motion patterns and apply priority-based masked sequence modeling to strengthen long-range spatio-temporal reasoning. Trained solely on synthetic data, MA-Mamba delivers substantial zero-shot gains on multiple real-world benchmarks, demonstrating strong robustness and generalizability.

PDF Details DOI

AAAI Conference 2026 Conference Paper

ZeRCP: Towards Communication-Efficient Collaborative Perception and Future Scene Prediction via Request-Free Spatial Filtering

  • Yijie Chen
  • Yuzhe Ji
  • Haotian Wang
  • Xiaoyun Qiu
  • Ying-Cong Chen
  • Xinhu Zheng

Multi-Agent collaboration addresses inherent limitations of individual agent systems, including limited sensing range and occlusion-induced blind spots. Despite significant progress, persistent challenges such as constrained communication bandwidth and under-explored subsequent extensions still hinder real-time deployment and further developments of collaborative autonomous driving systems. In this work, we propose ZeRCP, a unified communication-efficient framework that bridges collaborative perception with future scene prediction. Specifically, (i) we devise a plug-and-play request-free spatial filtering module (ZeroR) that eliminates the reliance on request maps while preserving inter-agent spatial complementarity modeling. This approach further reduce communication latency and bandwidth consumptions. (ii) We design a multi-scale pyramidal prediction network anchored by a novel Spatial-Temporal Deformable Attention (STDA) module, extending frame-wise detection to multi-frame predictions. This method adeptly models spatiotemporal dynamics without relying on auto-regressive recursion. We evaluate our method on a large-scale dataset in challenging semantic segmentation and scene prediction tasks. Extensive experiments demonstrate the superiority and effectiveness of ZeRCP in bandwidth-constrained collaboration scenarios and spatiotemporal prediction applications.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Adaptive Multi-Faceted Service Capabilities Co-Prediction for Nationwide Terminal Stations in Logistics

  • Shuxin Zhong
  • Kimberly Liu
  • Wenjun Lyu
  • Haotian Wang
  • Guang Wang
  • Yunhuai Liu
  • Tian He
  • Yu Yang

Estimating service capabilities for logistics terminal stations is essential for guiding operations adjustments to enhance customer experience. However, existing studies often focus on isolated metrics like on-time delivery or complaint rates, each reflecting a specific aspect of service capabilities. To provide a more comprehensive evaluation, we design AdaService, an Adaptive multi-faceted Service capabilities co-estimation framework. We begin by constructing Multi-faceted Hypergraph to encode stations using multiple performance metrics. We then introduce a Multi-faceted Hypergraph Convolution Network (MHCN) to capture the heterogeneous service capabilities across stations, providing a comprehensive capabilities representation. Finally, we apply an Adaptive Multi-faceted Estimation module that uses multi-task learning to model dynamic interactions among these metrics, enhancing predictive accuracy. Extensive evaluation with real-world data collected from nationwide stations in a leading logistics company in China demonstrates that AdaService significantly outperforms state-of-the-art methods, improving estimation accuracy for on-time delivery, on-time pick-up, and complaint rates by up to 18.98%, 9.30%, and 39.62%.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

  • Xinpeng Lv
  • Yunxin Mao
  • Haoxuan Li
  • Ke Liang
  • Jinxuan Yang
  • Wanrong Huang
  • Haoang Chi
  • Huan Chen

Strategic classification (SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, which are largely based on linear models or shallow neural networks, face significant limitations in terms of scalability and capacity when applied to real-world datasets with significantly increasing scale, especially in financial services and the internet sector. In this paper, we investigate how to leverage large language models to design a more scalable and efficient SC framework, especially in the case of growing individuals engaged with decision-making processes. Specifically, we introduce GLIM, a gradient-free SC method grounded in in-context learning. During the feed-forward process of self-attention, GLIM implicitly simulates the typical bi-level optimization process of SC, including both the feature manipulation and decision rule optimization. Without fine-tuning the LLMs, our proposed GLIM enjoys the advantage of cost-effective adaptation in dynamic strategic environments. Theoretically, we prove GLIM can support pre-trained LLMs to adapt to a broad range of strategic manipulations. We validate our approach through experiments with a collection of pre-trained LLMs on real-world and synthetic datasets in financial and internet domains, demonstrating that our GLIM exhibits both robustness and efficiency, and offering an effective solution for large-scale SC tasks.

PDF Details

NeurIPS Conference 2025 Conference Paper

Environment Inference for Learning Generalizable Dynamical System

  • Shixuan Liu
  • Yue He
  • Haotian Wang
  • Wenjing Yang
  • Yunfei Wang
  • Peng Cui
  • Zhong Liu

Data-driven methods offer efficient and robust solutions for analyzing complex dynamical systems but rely on the assumption of I. I. D. data, driving the development of generalization techniques for handling environmental differences. These techniques, however, are limited by their dependence on environment labels, which are often unavailable during training due to data acquisition challenges, privacy concerns, and environmental variability, particularly in large public datasets and privacy-sensitive domains. In response, we propose DynaInfer, a novel method that infers environment specifications by analyzing prediction errors from fixed neural networks within each training round, enabling environment assignments directly from data. We prove our algorithm effectively solves the alternating optimization problem in unlabeled scenarios and validate it through extensive experiments across diverse dynamical systems. Results show that DynaInfer outperforms existing environment assignment techniques, converges rapidly to true labels, and even achieves superior performance when environment labels are available.

PDF Details

ICML Conference 2025 Conference Paper

Federated Node-Level Clustering Network with Cross-Subgraph Link Mending

  • Jingxin Liu 0006
  • Renda Han
  • Wenxuan Tu
  • Haotian Wang
  • Junlong Wu
  • Jieren Cheng

Subgraphs of a complete graph are usually distributed across multiple devices and can only be accessed locally because the raw data cannot be directly shared. However, existing node-level federated graph learning suffers from at least one of the following issues: 1) heavily relying on labeled graph samples that are difficult to obtain in real-world applications, and 2) partitioning a complete graph into several subgraphs inevitably causes missing links, leading to sub-optimal sample representations. To solve these issues, we propose a novel $\underline{\text{Fed}}$erated $\underline{\text{N}}$ode-level $\underline{\text{C}}$lustering $\underline{\text{N}}$etwork (FedNCN), which mends the destroyed cross-subgraph links using clustering prior knowledge. Specifically, within each client, we first design an MLP-based projector to implicitly preserve key clustering properties of a subgraph in a denoising learning-like manner, and then upload the resultant clustering signals that are hard to reconstruct for subsequent cross-subgraph links restoration. In the server, we maximize the potential affinity between subgraphs stemming from clustering signals by graph similarity estimation and minimize redundant links via the N-Cut criterion. Moreover, we employ a GNN-based generator to learn consensus prototypes from this mended graph, enabling the MLP-GNN joint-optimized learner to enhance data privacy during data transmission and further promote the local model for better clustering. Extensive experiments demonstrate the superiority of FedNCN.

Details

NeurIPS Conference 2025 Conference Paper

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

  • Fengxiang Wang
  • Mingshuo Chen
  • Yueying Li
  • Di Wang
  • Haotian Wang
  • Zonghao Guo
  • Zefan Wang
  • Shan Boqi

Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce **SuperRS-VQA** (avg. 8, 376$\times$8, 376) and **HighRS-VQA** (avg. 2, 000$\times$1, 912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e. g. , ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: *Background Token Pruning* and *Anchored Token Selection*, to reduce the memory footprint while preserving key semantics. Integrating these techniques, we introduce **GeoLLaVA-8K**, the first RS-focused multimodal large language model capable of handling inputs up to 8K$\times$8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench. Datasets and code were released at https: //github. com/MiliLab/GeoLLaVA-8K.

PDF Details

NeurIPS Conference 2025 Conference Paper

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

  • Yang Shi
  • Huanqian Wang
  • Xie Xie
  • Huanyao Zhang
  • Lijie Zhao
  • Yifan Zhang
  • Xinfeng Li
  • Chaoyou Fu

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1, 464 videos with varying resolutions, aspect ratios, and durations, along with 2, 000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2. 5 Pro) achieves only an accuracy of 73. 7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.

PDF Details

NeurIPS Conference 2025 Conference Paper

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

  • Fengxiang Wang
  • Yulin Wang
  • Mingshuo Chen
  • Haotian Wang
  • Hongzhen Wang
  • Haiyan Zhao
  • Yangang Sun
  • Shuo Wang

Recent advances in self-supervised learning for Vision Transformers (ViTs) have fueled breakthroughs in remote sensing (RS) foundation models. However, the quadratic complexity of self-attention poses a significant barrier to scalability, particularly for large models and high-resolution images. While the linear-complexity Mamba architecture offers a promising alternative, existing RS applications of Mamba remain limited to supervised tasks on small, domain-specific datasets. To address these challenges, we propose RoMA, a framework that enables scalable self-supervised pretraining of Mamba-based RS foundation models using large-scale, diverse, unlabeled data. RoMA enhances scalability for high-resolution images through a tailored auto-regressive learning strategy, incorporating two key innovations: 1) a rotation-aware pretraining mechanism combining adaptive cropping with angular embeddings to handle sparsely distributed objects with arbitrary orientations, and 2) multi-scale token prediction objectives that address the extreme variations in object scales inherent to RS imagery. Systematic empirical studies validate that Mamba adheres to RS data and parameter scaling laws, with performance scaling reliably as model and data size increase. Furthermore, experiments across scene classification, object detection, and semantic segmentation tasks demonstrate that RoMA-pretrained Mamba models consistently outperform ViT-based counterparts in both accuracy and computational efficiency. The source code and pretrained models have be released at https: //github. com/MiliLab/RoMA.

PDF Details

AAAI Conference 2024 Conference Paper

Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees

  • Guang-Yuan Hao
  • Hengguan Huang
  • Haotian Wang
  • Jie Gao
  • Hao Wang

Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domain setting, where all data come from the same domain (e.g., the same dataset). However, many real-world tasks often involve multiple domains. For example, in visual recognition, it is often desirable to train an image classifier that works across different environments (e.g., different backgrounds), where images from each environment constitute one domain. Such a multi-domain AL setting is challenging for prior methods because they (1) ignore the similarity among different domains when assigning labeling budget and (2) fail to handle distribution shift of data across different domains. In this paper, we propose the first general method, dubbed composite active learning (CAL), for multi-domain AL. Our approach explicitly considers the domain-level and instance-level information in the problem; CAL first assigns domain-level budgets according to domain-level importance, which is estimated by optimizing an upper error bound that we develop; with the domain-level budgets, CAL then leverages a certain instance-level query strategy to select samples to label from each domain. Our theoretical analysis shows that our method achieves a better error bound compared to current AL methods. Our empirical results demonstrate that our approach significantly outperforms the state-of-the-art AL methods on both synthetic and real-world multi-domain datasets. Code is available at https://github.com/Wang-ML-Lab/multi-domain-active-learning.

PDF Details DOI

JBHI Journal 2024 Journal Article

EIRAD: An Evidence-Based Dialogue System With Highly Interpretable Reasoning Path for Automatic Diagnosis

  • Lian Yan
  • Yi Guan
  • Haotian Wang
  • Yi Lin
  • Yang Yang
  • Boran Wang
  • Jingchi Jiang

Dialogue System for Medical Diagnosis (DSMD) based on reinforcement learning (RL) can simulate patient-doctor interactions, playing a crucial role in clinical diagnosis. However, due to the complexity of disease etiology, DSMD faces the challenges of low efficiency in diagnostic evidence search. Moreover, solely RL-based DSMS, without the constraints of professional medical knowledge, often generates irrational, meaningless, or even erroneous symptom inquiries, leading to poor interpretability of diagnostic path and high misdiagnosis rates. To address these issues, we propose an E vidence-based dialogue system with highly I nterpretable R easoning path for A utomatic D iagnosis (EIRAD) grounded in medical knowledge graph (MKG). Specifically, our automated diagnostic model captures key symptoms for suspected diseases by explicitly leveraging the topology of MKG, enhancing the interpretability and accuracy of diagnosis. To expedite the retrieval of factual evidence, we develop two mechanisms: 1) Mapping mechanism between the entity set of MKG and DSMD's diagnostic evidence and diseases. According to the patient's symptoms, EIRAD prunes irrelevant disease and symptom nodes from the MKG, which can truncate the invalid action of RL-based DSMD. 2) Reward Mechanism of integrating the effectiveness of symptom inquiry and the accuracy of disease diagnosis. The comprehensive reward system is suitable for intelligent consultation, which can effectively drive DSMD to accelerate evidence collection. Experimental results demonstrate that our model significantly outperforms competitive benchmark methods in symptom inquiry efficiency and diagnostic accuracy.

Details DOI

TIST Journal 2024 Journal Article

Fine-grained Courier Delivery Behavior Recovery with a Digital Twin Based Iterative Calibration Framework

  • Fudan Yu
  • Guozhen Zhang
  • Haotian Wang
  • Depeng Jin
  • Yong Li

Recovering the fine-grained working process of couriers is becoming one of the essential problems for improving the express delivery systems because knowing the detailed process of how couriers accomplish their daily work facilitates the analyzing, understanding, and optimizing of the working procedure. Although coarse-grained courier trajectories and waybill delivery time data can be collected, this problem is still challenging due to noisy data with spatio-temporal biases, lacking ground truth of couriers’ fine-grained behaviors, and complex correlations between behaviors. Existing works typically focus on a single dimension of the process such as inferring the delivery time and can only yield results of low spatio-temporal resolution, which cannot address the problem well. To bridge the gap, we propose a digital-twin-based iterative calibration system (DTRec) for fine-grained courier working process recovery. We first propose a spatio-temporal bias correction algorithm, which systematically improves existing methods in correcting waybill addresses and trajectory stay points. Second, to model the complex correlations among behaviors and inherent physical constraints, we propose an agent-based model to build the digital twin of couriers. Third, to further improve recovery performance, we design a digital-twin-based iterative calibration framework, which leverages the inconsistency between the deduction results of the digital twin and the recovery results from real-world data to improve both the agent-based model and the recovery results. Experiments show that DTRec outperforms state-of-the-art baselines by 10.8% in terms of fine-grained accuracy on real-world datasets. The system is deployed in the industrial practices in JD Logistics with promising applications. The code is available at https://github.com/tsinghua-fib-lab/Courier-DTRec.

Details DOI

EAAI Journal 2024 Journal Article

Practical stabilization of highly nonlinear fuzzy hybrid complex networks via aperiodically intermittent discrete-time observation control

  • Wenhua Wang
  • Haotian Wang
  • Yongbao Wu
  • Wenxue Li

In this paper, the practical stabilization of highly nonlinear Takagi–Sugeno fuzzy complex networks with Markovian jump (HT-SFNM) is investigated via aperiodically intermittent discrete-time observation control (AID-TOC). Compared to existing articles on highly nonlinear complex networks, this paper considers both Takagi–Sugeno fuzzy rules and Markovian jump for the first time, and uses AID-TOC to solve its stability problem. Furthermore, more general polynomial growth conditions are adopted instead of the conventional linear growth conditions, which makes the model more universal. Finally, two numerical examples are presented to illustrate the effectiveness of the theoretical results.

Details DOI

TIST Journal 2024 Journal Article

RCCNet: A Spatial-Temporal Neural Network Model for Logistics Delivery Timely Rate Prediction

  • Jinhui Yi
  • Huan Yan
  • Haotian Wang
  • Jian Yuan
  • Yong Li

In logistics service, the delivery timely rate is a key experience indicator, which is highly essential to the competitive advantage of express companies. Prediction on it enables intervention on couriers with low predicted results in advance, thus ensuring employee productivity and customer satisfaction. Currently, few related works focus on couriers’ level delivery timely rate prediction, and there are complex spatial correlations between couriers and road districts in the express scenario, which makes traditional real-time prediction approaches hard to utilize. To deal with this, we propose a deep spatial-temporal neural network, RCCNet to model spatial-temporal correlations. Specifically, we adopt Node2vec, which can encode the road network-based graph directly to capture spatial correlations between road districts. Further, we calculate couriers’ historical time-series similarity to build a graph and employ graph convolutional networks to capture the correlation between couriers. We also leverage historical sequential information with long short-term memory networks. We conduct experiments with real-world express datasets. Compared with other competitive baseline methods widely used in industry, the experiment results demonstrate its superior performance over multiple baselines.

Details DOI

AAAI Conference 2024 Conference Paper

Scaling Few-Shot Learning for the Open World

  • Zhipeng Lin
  • Wenjing Yang
  • Haotian Wang
  • Haoang Chi
  • Long Lan
  • Ji Wang

Few-shot learning (FSL) aims to enable learning models with the ability to automatically adapt to novel (unseen) domains in open-world scenarios. Nonetheless, there exists a significant disparity between the vast number of new concepts encountered in the open world and the restricted available scale of existing FSL works, which primarily focus on a limited number of novel classes. Such a gap hinders the practical applicability of FSL in realistic scenarios. To bridge this gap, we propose a new problem named Few-Shot Learning with Many Novel Classes (FSL-MNC) by substantially enlarging the number of novel classes, exceeding the count in the traditional FSL setup by over 500-fold. This new problem exhibits two major challenges, including the increased computation overhead during meta-training and the degraded classification performance by the large number of classes during meta-testing. To overcome these challenges, we propose a Simple Hierarchy Pipeline (SHA-Pipeline). Due to the inefficiency of traditional protocols of EML, we re-design a lightweight training strategy to reduce the overhead brought by much more novel classes. To capture discriminative semantics across numerous novel classes, we effectively reconstruct and leverage the class hierarchy information during meta-testing. Experiments show that the proposed SHA-Pipeline significantly outperforms not only the ProtoNet baseline but also the state-of-the-art alternatives across different numbers of novel classes.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

A Prediction-and-Scheduling Framework for Efficient Order Transfer in Logistics

  • Wenjun Lyu
  • Haotian Wang
  • Yiwei Song
  • Yunhuai Liu
  • Tian He
  • Desheng Zhang

Order Transfer from the transfer center to delivery stations is an essential and expensive part of the logistics service chain. In practice, one vehicle sends transferred orders to multiple delivery stations in one transfer trip to achieve a better trade-off between the transfer cost and time. A key problem is generating the vehicle’s route for efficient order transfer, i. e. , minimizing the order transfer time. In this paper, we explore fine-grained delivery station features, i. e. , downstream couriers’ remaining working times in last-mile delivery trips and the transferred order distribution to design a Prediction-and-Scheduling framework for efficient Order Transfer called PSOT, including two components: i) a Courier’s Remaining Working Time Prediction component to predict each courier’s working time for conducting heterogeneous tasks, i. e. , order pickups and deliveries, with a context-aware location embedding and an attention-based neural network; ii) a Vehicle Scheduling component to generate the vehicle’s route to served delivery stations with an order-transfer-time-aware heuristic algorithm. The evaluation results with real-world data from one of the largest logistics companies in China show PSOT improves the courier’s remaining working time prediction by up to 35. 6% and reduces the average order transfer time by up to 51. 3% compared to the state-of-the-art methods.

PDF Details DOI
v2026.09.13