Lianhui Qin

5 papers University of California, San Diego

• KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
• REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
• SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
• Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
• Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs