activity
20242026
most citedSeeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs

3 citations · 3 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV2026

Context Tokens are Anchors: Understanding the Repetition Curse in dMLLMs from an Information Flow Perspective

Qiyan Zhao, Xiaofeng Zhang, Shuochen Chang +7

Recent diffusion-based Multimodal Large Language Models (dMLLMs) suffer from high inference latency and therefore rely on caching techniques to accelerate decoding. However, the ap…

cs.CV2026

Hallucination Begins Where Saliency Drops

Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu +8

Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguis…

cs.AI2025

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

Yue Xin, Chen Shen, Shaotian Yan +5

Chain-of-Thought (CoT) prompting enhances the math reasoning capability of large language models (LLMs) to a large margin. However, the mechanism underlying such improvements remai…

cs.CV2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

Qiyan Zhao, Xiaofeng Zhang, Yiheng Li +7

Hallucinations pose a significant challenge in Large Vision Language Models (LVLMs), with misalignment between multimodal features identified as a key contributing factor. This pap…

cs.CL2025

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

Kaiyuan Liu, Chen Shen, Zhanwei Zhang +3

While recent advances in large reasoning models have demonstrated remarkable performance, efficient reasoning remains critical due to the rapid growth of output length. Existing op…

cs.CL2025

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Sinan Fan, Liang Xie, Chen Shen +7

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our inv…