10 papers
PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders
Man Jiang, Ouxiang Li, Weibao Xue +4
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations,…
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…
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
Xiqiao Xiong, Ouxiang Li, Zhuo Liu +5
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of trai…
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…
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
Ouxiang Li, Yuan Wang, Xinting Hu +7
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two…
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
Ouxiang Li, Yuan Wang, Xinting Hu +3
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, a…