Lianhui Qin

Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving

Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise