共计 147 篇文章
2025
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
Investigating Spatial Attention Bias in Vision-Language Models
Steer LLM Latents for Hallucination Detection
Agentic Context Engineering：面向自改进语言模型的动态上下文演化
Neural Message-Passing on Attention Graphs for Hallucination Detection
Think-on-Graph： Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
AVG-LLaVA： 一种具有自适应视觉粒度的高效大型多模态模型
Martingale Score： An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
VISUAL AGENTS AS FAST AND SLOW THINKERS
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality