Xu Han

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention ACL 2026 ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs ACL 2026 AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage ACL 2026 CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis AAAI 2026 CheckRLM: Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented Reasoning ACL 2026 CPT-Agent: A Cognitive Process Theory-driven Framework for Student Simulation in Writing Development ACL 2026 Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning AAAI 2026 EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization AAAI 2026 LumiX: Structured and Coherent Text-to-Intrinsic Generation CVPR 2026 MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe CVPR 2026 Phantom: Physical Object Interactions as Dynamic Triggers for NMS-Exploited Backdoors CVPR 2026 APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs ACL 2025 AutoClean: LLMs Can Prepare Their Training Corpus NAACL 2025 CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China EMNLP 2025 Cognitive Mirroring for DocRE: A Self-Supervised Iterative Reflection Framework with Triplet-Centric Explicit and Implicit Feedback ACL 2025 Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025 DeepNote: Note-Centric Deep Retrieval-Augmented Generation EMNLP 2025 Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning ICLR 2025 Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation CVPR 2025 FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling ACL 2025 HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss ICCV 2025 KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases EMNLP 2025 LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models ACL 2025 MDAA-Diff: CT-Guided Multi-Dose Adaptive Attention Diffusion Model for PET Denoising MICCAI 2025 More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding AAAI 2025 MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning CVPR 2025 Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages ACL 2025 Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slips COLING 2025 PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models EMNLP 2025 PDF-Net: Prototype-Aware Dynamic Fusion Network for Nasopharyngeal Carcinoma T-staging Classification with Epstein-Barr Virus DNA MICCAI 2025 PLUS: Plug-and-Play Enhanced Liver Lesion Diagnosis Model on Non-Contrast CT Scans MICCAI 2025 Progressive Compositionality in Text-to-Image Generative Models ICLR 2025 ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models COLING 2025 RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework ACL 2025 Refining Cervical Cell Classification with Cytological Knowledge and Optimal Attribute Descriptor Matching MICCAI 2025 RSAD: Region-Specific Anomaly Detection in fMRI for Disease Diagnosis MICCAI 2025 SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds CVPR 2025 Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning MICCAI 2025 Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training NAACL 2025 Sparsing Law: Towards Large Language Models with Greater Activation Sparsity ICML 2025 TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators ACL 2025 VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents ICLR 2025 WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting ICML 2025 ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning ICLR 2024 ∞Bench: Extending Long Context Evaluation Beyond 100K Tokens ACL 2024 Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models EMNLP 2024 CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables ICML 2024 Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models NeurIPS 2024 Exploring the Benefit of Activation Sparsity in Pre-training ICML 2024 FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection ACL 2024 Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training COLING 2024 High-Order Semantic Alignment for Unsupervised Fine-Grained Image-Text Retrieval COLING 2024 InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory NeurIPS 2024 Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages ICLR 2024 LIDIA: Precise Liver Tumor Diagnosis on Multi-Phase Contrast-Enhanced CT via Iterative Fusion and Asymmetric Contrastive Learning MICCAI 2024 Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models EMNLP 2024 LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks ACL 2024 MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization ACL 2024 MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation ACL 2024 MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models AAAI 2024 MUCH: A Multimodal Corpus Construction for Conversational Humor Recognition Based on Chinese Sitcom COLING 2024 OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems ACL 2024 OneBit: Towards Extremely Low-bit Large Language Models NeurIPS 2024 Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding EMNLP 2024 patchDPCC: A Patchwise Deep Compression Framework for Dynamic Point Clouds AAAI 2024 Predicting Emergent Abilities with Infinite Resolution Evaluation ICLR 2024 Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis ACL 2024 Robust and Scalable Model Editing for Large Language Models COLING 2024 Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents EMNLP 2024 Training-free Multi-objective Diffusion Model for 3D Molecule Generation ICLR 2024 UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs ACL 2024 UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset ACL 2024 V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception ECCV 2024 Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models EMNLP 2023 Chinese Metaphorical Relation Extraction EMNLP 2023 Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling ICML 2023 Emergent Modularity in Pre-trained Transformers ACL 2023 Fitting Autoregressive Graph Generative Models through Maximum Likelihood Estimation JMLR 2023 H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training NeurIPS 2023 PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer ACL 2023 Plug-and-Play Document Modules for Pre-trained Models ACL 2023 Plug-and-Play Knowledge Injection for Pre-trained Language Models ACL 2023 Recyclable Tuning for Continual Pre-training ACL 2023 Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning ACL 2023 Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model NeurIPS 2023 Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules EMNLP 2023 WebCPM: Interactive Web Search for Chinese Long-form Question Answering ACL 2023 BMCook: A Task-agnostic Compression Toolkit for Big Models EMNLP 2022 BMInf: An Efficient Toolkit for Big Model Inference and Tuning ACL 2022 Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages ACL 2022 Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuning EMNLP 2022 Exploring Mode Connectivity for Pre-trained Language Models EMNLP 2022 Fully Hyperbolic Neural Networks ACL 2022 GACT: Activation Compressed Training for Generic Network Architectures ICML 2022 Knowledge Inheritance for Pre-trained Language Models NAACL 2022 MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction EMNLP 2022 PPT: Pre-trained Prompt Tuning for Few-shot Learning ACL 2022 Predicting Physics in Mesh-reduced Space with Temporal Attention ICLR 2022 Prompt-learning for Fine-grained Entity Typing EMNLP 2022 Adversarial Language Games for Advanced Natural Language Intelligence AAAI 2021 CLEVE: Contrastive Pre-training for Event Extraction ACL 2021 Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference IJCAI 2021 Few-NERD: A Few-shot Named Entity Recognition Dataset ACL 2021 GAN Ensemble for Anomaly Detection AAAI 2021 Local Temperature Scaling for Probability Calibration ICCV 2021 Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction ACL 2021 Open Hierarchical Relation Extraction NAACL 2021 Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation ICML 2021 Visual Distant Supervision for Scene Graph Generation ICCV 2021 Collecting Verified COVID-19 Question Answer Pairs EMNLP 2020 Continual Relation Learning via Episodic Memory Activation and Reconsolidation ACL 2020 Denoising Relation Extraction from Document-level Distant Supervision EMNLP 2020 Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph EMNLP 2020 Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training AAAI 2020 IsOBS: An Information System for Oracle Bone Script EMNLP 2020 Learning from Context or Names? An Empirical Study on Neural Relation Extraction EMNLP 2020 MAVEN: A Massive General Domain Event Detection Dataset EMNLP 2020 Meta-Information Guided Meta-Learning for Few-Shot Relation Classification COLING 2020 More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction AACL 2020 Neural Gibbs Sampling for Joint Event Argument Extraction AACL 2020 Neural Snowball for Few-Shot Relation Learning AAAI 2020 Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations EMNLP 2019 Adversarial Training for Weakly Supervised Event Detection NAACL 2019 DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction ACL 2019 DocRED: A Large-Scale Document-Level Relation Extraction Dataset ACL 2019 ERNIE: Enhanced Language Representation with Informative Entities ACL 2019 FewRel 2.0: Towards More Challenging Few-Shot Relation Classification EMNLP 2019 GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification ACL 2019 HMEAE: Hierarchical Modular Event Argument Extraction EMNLP 2019 Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification AAAI 2019 Networks for Joint Affine and Non-Parametric Image Registration CVPR 2019 OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction EMNLP 2019 Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data EMNLP 2019 Quantifying Similarity between Relations with Fact Distribution ACL 2019 Adversarial Multi-lingual Neural Relation Extraction COLING 2018 Complementary Binary Quantization for Joint Multiple Indexing IJCAI 2018 FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation EMNLP 2018 Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention EMNLP 2018 OpenKE: An Open Toolkit for Knowledge Embedding EMNLP 2018 Put It Back: Entity Typing with Language Model Enhancement EMNLP 2018 UIR-PKU: Twitter-OpinMiner System for Sentiment Analysis in Twitter at SemEval 2015 SemEval 2015