Yuxuan Chen (陈宇轩)

I'm a first-year Ph.D. student from School of Mechanical Engineering, Shanghai Jiao Tong University. I am currently advised by Prof. Xiao Li. My research interests include efficient robotic policies, large language models, and embodied AI.

Email  /  Google Scholar  /  GitHub

Shanghai Jiao Tong University (SJTU)
School of Mechanical Engineering

Shanghai Jiao Tong University (SJTU)
School of Mechanical Engineering
Major in Mechanical Engineering

Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation
Yuxuan Chen, Wanruo Zhang, Xiao Li
ArXiv, 2608.14379
paper / website /

We present ReflexBench, a latency-aware benchmark for reaction-critical manipulation, and propose ReflexVLA, an efficient VLA that combines latent future prediction, multi-frame temporal fusion, and low-latency inference. ReflexVLA improves dynamic manipulation while remaining competitive on static benchmarks, and is further validated in real-world deployment.

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
Yuxuan Chen, Yixin Han, Yize Huang, Xiao Li
IEEE Robotics and Automation Letters (RA-L), 2026
paper / website /

We propose RLRC, a three-stage recovery method for compressed VLAs, including structured pruning, performance recovery based on SFT and RL, and further quantization. RLRC achieves up to an 8x reduction in memory usage and a 2.3x improvement in inference throughput, while maintaining or even surpassing the original VLA's task success rate.

FASTNav: Fine-Tuned Adaptive Small-Language-Models Trained for Multi-Point Robot Navigation
Yuxuan Chen, Yixin Han, Xiao Li
IEEE Robotics and Automation Letters (RA-L), 2024
paper

We propose FASTNav - a method for boosting lightweight LLMs, also known as small language models (SLMs), for robot navigation. The proposed method contains three modules: fine-tuning, teacher-student iteration, and language-based multi-point robot navigation. We train and evaluate models with FASTNav in both simulation and real robots, proving that we can deploy them with low cost, high accuracy and low response time.

I borrowed this website layout from here!