4 citations · 9 across the 11 of their papers we have counts for
12 papers
HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence
Xiqiao Xiong, Moxin Li, Zhixin Ma +4
Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace manual harness adaptation, mot…
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…
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…
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…
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…
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,…
Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective
Ouxiang Li, Jiayin Cai, Yanbin Hao +3
With recent generative models facilitating photo-realistic image synthesis, the proliferation of synthetic images has also engendered certain negative impacts on social platforms,…
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
Ouxiang Li, Yanbin Hao, Zhicai Wang +4
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MI…
A Sanity Check for AI-generated Image Detection
Shilin Yan, Ouxiang Li, Jiayin Cai +4
With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity…
Bi-directional Distribution Alignment for Transductive Zero-Shot Learning
Zhicai Wang, Yanbin Hao, Tingting Mu +3
It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not mat…