Yufei Ding

3 papers University of California, San Diego

• KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
• SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
• Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding