activity
20242026
collaborators

10 papers

cs.CV2026

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

Shuliang Liu, Songbo Yang, Dong Fang +7

Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models b…

cs.CV2025

Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning

Jialong Qin, Xin Zou, Di Lu +2

Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant…

cs.CV2025

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou, Di Lu, Yizhou Wang +5

Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent…

cs.CL2025

DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning

Yibo Yan, Guangwei Xu, Xin Zou +3

Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applicat…

cs.CL2025

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning

Jianghangfan Zhang, Yibo Yan, Kening Zheng +3

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual percep…

cs.CL2025

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis

Haoming Huang, Yibo Yan, Jiahao Huo +4

Large Language Models (LLMs), despite their remarkable capabilities, are hampered by hallucinations. A particularly challenging variant, knowledge overshadowing, occurs when one pi…