2 papers
cs.CV2026
ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs
Yijing Du, Xiangcheng Zhan, Shuo Yang
Large Vision-Language Models (LVLMs) frequently suffer from object hallucination. Existing training-free interventions primarily manipulate attention weights, which indirectly affe…
cs.AI2026
Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation
Xiangcheng Zhan, Zirui Chen, Yicheng Zhao +2
World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning paradigms typically improve beha…