Xuming Hu

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods ACL 2026 Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models AAAI 2026 DualScope: Capturing Critical Spatial and Temporal Cues for Distracted Driving Activity Recognition AAAI 2026 Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design ACL 2026 Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning AAAI 2026 Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering ACL 2026 A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges ACL 2025 A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models ACL 2025 Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? ACL 2025 Can Watermarked LLMs be Identified by Users via Crafted Prompts? ICLR 2025 Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models ACL 2025 Dataset Distillation with Neural Characteristic Function: A Minmax Perspective CVPR 2025 Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning ACL 2025 Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction EMNLP 2025 DiscoverGPT: Multi-task Fine-tuning Large Language Model for Related Table Discovery NAACL 2025 Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? EMNLP 2025 Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation EMNLP 2025 EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models ACL 2025 Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios EMNLP 2025 Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers ICLR 2025 ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models CVPR 2025 Internal Chain-of-Thought: Empirical Evidence for Layer‐wise Subtask Scheduling in LLMs EMNLP 2025 LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching ICCV 2025 LLM Agents for Education: Advances and Applications EMNLP 2025 Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models ICML 2025 MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection ACL 2025 Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality ICLR 2025 MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models ACL 2025 OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation ICCV 2025 OneForecast: A Universal Framework for Global and Regional Weather Forecasting ICML 2025 PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions EMNLP 2025 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025 PolyJoin: Semantic Multi-key Joinable Table Search in Data Lakes NAACL 2025 RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning ICML 2025 Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization ICCV 2025 Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models ACL 2025 Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction ACL 2025 SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning ACL 2025 StructFact: Reasoning Factual Knowledge from Structured Data with Large Language Models ACL 2025 UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models ACL 2025 Unlocking Speech Instruction Data Potential with Query Rewriting ACL 2025 VLA-Mark: A cross modal watermark for large vision-language alignment models EMNLP 2025 An Unforgeable Publicly Verifiable Watermark for Large Language Models ICLR 2024 A Semantic Invariant Robust Watermark for Large Language Models ICLR 2024 Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions ACL 2024 LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments ACL 2024 LongGenBench: Long-context Generation Benchmark EMNLP 2024 MarkLLM: An Open-Source Toolkit for LLM Watermarking EMNLP 2024 Mind’s Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models NAACL 2024 MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model EMNLP 2024 On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations ACL 2024 Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities EMNLP 2024 Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network AAAI 2024 Towards Understanding Factual Knowledge of Large Language Models ICLR 2024 Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications EMNLP 2024 When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models NeurIPS 2024 AMR-based Network for Aspect-based Sentiment Analysis ACL 2023 Automatic Table Union Search with Tabular Representation Learning ACL 2023 Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer ACL 2023 Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks ACL 2023 Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing ACL 2023 GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks ACL 2023 Graph Component Contrastive Learning for Concept Relatedness Estimation AAAI 2023 Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis ACL 2023 RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction EMNLP 2023 Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution EMNLP 2022 CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking NAACL 2022 Domain-Specific NER via Retrieving Correlated Samples COLING 2022 HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction NAACL 2022 Query-based Instance Discrimination Network for Relational Triple Extraction EMNLP 2022 Scene Graph Modification as Incremental Structure Expanding COLING 2022 Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction EMNLP 2021 Semi-supervised Relation Extraction via Incremental Meta Self-Training EMNLP 2021 SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction EMNLP 2020