Showing 2026Show all
3 papers · 1 filter
cs.CV2026
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
Zhenchen Tang, Yang Li, Songlin Yang +6
Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often…
cs.CV2026
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
Zichuan Wang, Songlin Yang, Bo Peng +4
Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image. Prior work largely attributes this to insufficient v…
cs.AI2026
Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models
Zhenchen Tang, Songlin Yang, Zichuan Wang +4
Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks…