PPaperPicks

Xuming Hu

Hong Kong University of Science and Technology Guangzhou (HKUST-GZ), Guangzhou, China

73 papers at tracked venues · 56 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-6075-4224 ↗Homepage ↗

Venues

ACL ×26EMNLP ×14ICLR ×6NeurIPS ×5AAAI ×4CVPR ×3ICCV ×3ICML ×3NAACL ×3SIGIR ×2SIGKDD ×2ACM MM ×1ICDE ×1

Frequent coauthors

Yibo Yan
DBLP profile ↗ORCID search ↗
×5
Aiwei Liu
DBLP profile ↗ORCID search ↗
×4
Junzhuo Li
DBLP profile ↗ORCID search ↗
×3
Shuliang Liu
DBLP profile ↗ORCID search ↗
×3
Shaobo Wang
DBLP profile ↗ORCID search ↗
×3
Chenfei Liao
DBLP profile ↗ORCID search ↗
×2
Leyi Pan
DBLP profile ↗ORCID search ↗
×2
Xiang Liu
DBLP profile ↗ORCID search ↗
×2
Xin Zou
DBLP profile ↗ORCID search ↗
×2
Sirui Huang
DBLP profile ↗ORCID search ↗
×2
Junzhe Chen
DBLP profile ↗ORCID search ↗
×2
Jiahao Huo
DBLP profile ↗ORCID search ↗
×2

Papers

  1. Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
    ACL 2026 ·
    Chenfei Liao
    DBLP profile ↗ORCID search ↗
  2. CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity
    SIGKDD 2026 ·
    Kaiwen Xia
    DBLP profile ↗ORCID search ↗
  3. Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation
    SIGKDD 2026 ·
    Siyuan Li
    DBLP profile ↗ORCID search ↗
  4. Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models
    AAAI 2026 ·
    Bo Wang
    DBLP profile ↗ORCID search ↗
  5. DualScope: Capturing Critical Spatial and Temporal Cues for Distracted Driving Activity Recognition
    AAAI 2026 ·
    Zhijie Qiu
    DBLP profile ↗ORCID search ↗
  6. ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
    ACL 2026 ·
    Yibo Yan
    DBLP profile ↗ORCID search ↗
  7. Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
    ACL 2026 ·
    Junzhuo Li
    DBLP profile ↗ORCID search ↗
  8. Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
    ACL 2026 ·
    Yibo Yan
    DBLP profile ↗ORCID search ↗
  9. Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
    ACL 2026 ·
    Yibo Yan
    DBLP profile ↗ORCID search ↗
  10. Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning
    AAAI 2026 ·
    Jialong Qin
    DBLP profile ↗ORCID search ↗
  11. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
    ACL 2026 ·
    Junxi Wang
    DBLP profile ↗ORCID search ↗
  12. Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs
    ACL 2026 ·
    Yubo Gao
    DBLP profile ↗ORCID search ↗
  13. Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
    ACL 2026 ·
    Shuliang Liu
    DBLP profile ↗ORCID search ↗
  14. A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
    ACL 2025 ·
    Yibo Yan
    DBLP profile ↗ORCID search ↗
  15. A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
    ACL 2025 ·
    Shuliang Liu
    DBLP profile ↗ORCID search ↗
  16. Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness
    CVPR 2025 ·
    Chenfei Liao
    DBLP profile ↗ORCID search ↗
  17. Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
    ACL 2025 ·
    Leyi Pan
    DBLP profile ↗ORCID search ↗
  18. Can Watermarked LLMs be Identified by Users via Crafted Prompts?
    ICLR 2025 ·
    Aiwei Liu
    DBLP profile ↗ORCID search ↗
  19. Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
    ACL 2025 ·
    Yanggan Gu
    DBLP profile ↗ORCID search ↗
  20. ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
    NeurIPS 2025 ·
    Xiang Liu
    DBLP profile ↗ORCID search ↗
  21. Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning
    ACL 2025 ·
    Shaobo Wang
    DBLP profile ↗ORCID search ↗
  22. Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
    CVPR 2025 ·
    Shaobo Wang
    DBLP profile ↗ORCID search ↗
  23. DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction
    EMNLP 2025 ·
    Jian Chen
    DBLP profile ↗ORCID search ↗
  24. Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis
    ACL 2025 ·
    Junzhuo Li
    DBLP profile ↗ORCID search ↗
  25. DiscoverGPT: Multi-task Fine-tuning Large Language Model for Related Table Discovery
    NAACL 2025 · Xuming Hu
  26. Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?
    EMNLP 2025 ·
    Junyan Zhang
    DBLP profile ↗ORCID search ↗
  27. Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
    NeurIPS 2025 ·
    Xin Zou
    DBLP profile ↗ORCID search ↗
  28. Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation
    EMNLP 2025 ·
    Junzhuo Li
    DBLP profile ↗ORCID search ↗
  29. EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
    ACL 2025 ·
    Jiamin Su
    DBLP profile ↗ORCID search ↗
  30. Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
    EMNLP 2025 ·
    Yunkai Dang
    DBLP profile ↗ORCID search ↗
  31. From Guesswork to Guarantee: Towards Faithful Multimedia Web Forecasting with TimeSieve
    ACM MM 2025 ·
    Songning Lai
    DBLP profile ↗ORCID search ↗
  32. Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
    ICLR 2025 ·
    Shaobo Wang
    DBLP profile ↗ORCID search ↗
  33. HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge
    SIGIR 2025 ·
    Sirui Huang
    DBLP profile ↗ORCID search ↗
  34. ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
    CVPR 2025 ·
    Junzhe Chen
    DBLP profile ↗ORCID search ↗
  35. Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
    EMNLP 2025 ·
    Zhipeng Yang
    DBLP profile ↗ORCID search ↗
  36. LLM Agents for Education: Advances and Applications
    EMNLP 2025 ·
    Zhendong Chu
    DBLP profile ↗ORCID search ↗
  37. LazyMAR: Accelerating Masked Autoregressive Models Via Feature Caching
    ICCV 2025 ·
    Feihong Yan
    DBLP profile ↗ORCID search ↗
  38. LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
    NeurIPS 2025 ·
    Junyu Chen
    DBLP profile ↗ORCID search ↗
  39. Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
    ICML 2025 ·
    Xin Zou
    DBLP profile ↗ORCID search ↗
  40. MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
    ACL 2025 ·
    Jiahao Huo
    DBLP profile ↗ORCID search ↗
  41. MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
    ACL 2025 ·
    Yibo Yan
    DBLP profile ↗ORCID search ↗
  42. Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
    ICLR 2025 ·
    Guanyu Zhou
    DBLP profile ↗ORCID search ↗
  43. OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
    ICCV 2025 ·
    Ding Zhong
    DBLP profile ↗ORCID search ↗
  44. OneForecast: A Universal Framework for Global and Regional Weather Forecasting
    ICML 2025 ·
    Yuan Gao
    DBLP profile ↗ORCID search ↗
  45. PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions
    EMNLP 2025 ·
    Song Dai
    DBLP profile ↗ORCID search ↗
  46. Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
    EMNLP 2025 ·
    Haoming Huang
    DBLP profile ↗ORCID search ↗
  47. PolyJoin: Semantic Multi-key Joinable Table Search in Data Lakes
    NAACL 2025 · Xuming Hu
  48. RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
    NeurIPS 2025 ·
    Shuhang Xun
    DBLP profile ↗ORCID search ↗
  49. RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
    ICML 2025 ·
    Yuanhuiyi Lyu
    DBLP profile ↗ORCID search ↗
  50. Reducing Unimodal Bias in Multi-Modal Semantic Segmentation With Multi-Scale Functional Entropy Regularization
    ICCV 2025 ·
    Xu Zheng
    DBLP profile ↗ORCID search ↗
  51. Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
    ACL 2025 ·
    Kening Zheng
    DBLP profile ↗ORCID search ↗
  52. Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
    ACL 2025 ·
    Yinghui Li
    DBLP profile ↗ORCID search ↗
  53. SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
    ACL 2025 ·
    Junkai Chen
    DBLP profile ↗ORCID search ↗
  54. StructFact: Reasoning Factual Knowledge from Structured Data with Large Language Models
    ACL 2025 ·
    Sirui Huang
    DBLP profile ↗ORCID search ↗
  55. UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
    ACL 2025 ·
    Boyang Xue
    DBLP profile ↗ORCID search ↗
  56. UltraWiki: Ultra-Fine-Grained Entity Set Expansion with Negative Seed Entities
    ICDE 2025 ·
    Yangning Li
    DBLP profile ↗ORCID search ↗
  57. Unlocking Speech Instruction Data Potential with Query Rewriting
    ACL 2025 ·
    Yonghua Hei
    DBLP profile ↗ORCID search ↗
  58. VLA-Mark: A cross modal watermark for large vision-language alignment models
    EMNLP 2025 ·
    Shuliang Liu
    DBLP profile ↗ORCID search ↗
  59. A Semantic Invariant Robust Watermark for Large Language Models
    ICLR 2024 ·
    Aiwei Liu
    DBLP profile ↗ORCID search ↗
  60. An Unforgeable Publicly Verifiable Watermark for Large Language Models
    ICLR 2024 ·
    Aiwei Liu
    DBLP profile ↗ORCID search ↗
  61. Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions
    ACL 2024 · Xuming Hu
  62. LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
    ACL 2024 ·
    Junzhe Chen
    DBLP profile ↗ORCID search ↗
  63. LongGenBench: Long-context Generation Benchmark
    EMNLP 2024 ·
    Xiang Liu
    DBLP profile ↗ORCID search ↗
  64. MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model
    EMNLP 2024 ·
    Jiahao Huo
    DBLP profile ↗ORCID search ↗
  65. MarkLLM: An Open-Source Toolkit for LLM Watermarking
    EMNLP 2024 ·
    Leyi Pan
    DBLP profile ↗ORCID search ↗
  66. Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models
    NAACL 2024 ·
    Weize Liu
    DBLP profile ↗ORCID search ↗
  67. On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations
    ACL 2024 ·
    Shiao Meng
    DBLP profile ↗ORCID search ↗
  68. Preventing and Detecting Misinformation Generated by Large Language Models
    SIGIR 2024 ·
    Aiwei Liu
    DBLP profile ↗ORCID search ↗
  69. Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities
    EMNLP 2024 ·
    Zhonghao Li
    DBLP profile ↗ORCID search ↗
  70. Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network
    AAAI 2024 · Xuming Hu
  71. Towards Understanding Factual Knowledge of Large Language Models
    ICLR 2024 · Xuming Hu
  72. Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications
    EMNLP 2024 ·
    Weize Liu
    DBLP profile ↗ORCID search ↗
  73. When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
    NeurIPS 2024 ·
    Yinghui Li
    DBLP profile ↗ORCID search ↗