6 papers
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…
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…
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…
Instant Preference Alignment for Text-to-Image Diffusion Models
Yang Li, Songlin Yang, Xiaoxuan Han +4
Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Pr…
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective
Xiaoxuan Han, Songlin Yang, Wei Wang +2
Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this,…
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
Yang Li, Songlin Yang, Wei Wang +3
Highly realistic AI generated face forgeries known as deepfakes have raised serious social concerns. Although DNN-based face forgery detection models have achieved good performance…