Xinyuan Li
I am a junior undergraduate at Zhejiang University, majoring in Automation Engineering. I am also enrolled in the ACEE Honors Program at Chu Kochen Honors College.
I am currently a Research Intern at MLL Lab, Northwestern University, advised by Prof. Manling Li. My current work studies latency-sensitive evaluation for real-time VLA control and efficient infrastructure for model training and simulation.

Research Interests
- Multimodal Foundation Models & World Action Models (WAMs): Exploring VLMs, UMMs, VLAs, and WAMs for perception, reasoning, world modeling, and action.
- Reinforcement Learning: Studying decision-making and policy learning in interactive environments.
- Efficient AI Systems: Building GPU/CUDA environment acceleration, KV streaming cache, FlexAttention masks, and training/inference optimizations.
News
- We introduce LAGEN, a framework for evaluating and training vision-language agents under deployment latency.
Selected Publications

MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
arXiv preprint, 2026* Equal contribution.
Education
