Yang Zhou

7 papers University of Toronto

• Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
• Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
• Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding
• PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
• SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data
• The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
• VividFace: A Robost and High-Fidelity Video Face Swapping Framework