- Papers: WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents, RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models, Improving Your Model Ranking on Chatbot Arena by Vote Rigging, RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style, Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense, A Watermark-Conditioned Diffusion Model for IP Protection, Towards Stable Backdoor Purification with Feature Shift Tuning, Identification of the Adversary from a Single Adversarial Example