共计 42 篇文章

---

2026

03-12

Why LVLMs Are More Prone to Hallucinations in Longer Responses： The Role of Context

03-09

HALP： Detecting Hallucinations in Vision-Language Models without Generating a Single Token

03-08

Lyapunov Probes for Hallucination Detection in Large Foundation Models

02-09

Hallucination Begins Where Saliency Drops

2025

12-27

SmartSight：通过时间注意力坍缩在不损害视频理解的前提下缓解视频大模型中的幻觉问题

12-25

Investigating Spatial Attention Bias in Vision-Language Models

12-24

T5Gemma2

12-15

AVG-LLaVA： 一种具有自适应视觉粒度的高效大型多模态模型

12-12

VISUAL AGENTS AS FAST AND SLOW THINKERS

12-11

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality