PPL
Yuxin Chen
Papers (9)
Learning to Act under Noise: Enhancing Agent Robustness via Noisy EnvironmentsVitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User InteractionsTiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few PromptsSemantic Generative Tuning for Unified Multimodal ModelsReasoning Can Be Restored by Correcting a Few Decision TokensLoKA: Low-precision Kernel Applications for Recommendation Models At ScaleSelf-ReSET: Learning to Self-Recover from Unsafe Reasoning TrajectoriesInternalizing Safety Understanding in Large Reasoning Models via VerificationSkill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning