16 papers
UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation
Yao Huang, Yitong Sun, Huanran Chen +8
Despite the impressive generative capabilities of text-to-image diffusion models, they remain vulnerable to implicit sexual prompts, where subtle cues disguised as benign terms or…
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
Yihao Zhang, Zeming Wei, Xiaokun Luan +7
The paper introduces AgentWorm, a self-replicating worm that can autonomously infect and spread across large-scale LLM-based agent ecosystems by hijacking configurations and execut…
Reinforcement Learning from Denoising Feedback
Qi He, Huan Chen, Ya Guo +3
Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs). We introduce Reinforcement Learning fr…
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
Huanran Chen, Huaqing Zhang, Xiao Li +3
The foundational capabilities of large language models are acquired during pretraining on internet-scale, highly heterogeneous data mixtures. In this work, we investigate an intere…
Alignment Dynamics in LLM Fine-Tuning
Yuhan Huang, Huanran Chen, Yinpeng Dong
Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under s…
Diffusion Models as Dataset Distillation Priors
Duo Su, Huyu Wu, Huanran Chen +4
Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization…