Zhiting Hu

7 papers University of California, San Diego

• Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
• Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
• Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
• SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
• Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
• Towards General Continuous Memory for Vision-Language Models
• scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery