From the 1 of 5 linked papers with an AI index.
5 papers
Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition
Qifan Zhou, Yuan Wang, Yanbin Hao +4
The paper introduces Uni-AdaVD, an inference-time framework that removes unwanted concepts from visual generative models by orthogonalizing and shifting value representations, work…
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
Yuan Wang, Ouxiang Li, Yulong Xu +8
Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the quality of video reward models (RM…
Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR
Jinda Lu, Junkang Wu, Jinghan Li +6
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and…
Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
Yuan Wang, Borui Liao, Huijuan Huang +5
Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality…
Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
Yuan Wang, Ouxiang Li, Tingting Mu +4
Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts,…