|
I am a Master's student in the Electrical and Computer Engineering department at University of Washington. Currently, I am a member of NeuroAI Lab advised by Prof. Eli Shlizerman. My research interests include Audio-Visual Learning, Spatial Reasoning. Before UW, I was a research assistant at State Key Laboratory of CAD&CG in College of Computer Science and Technology at Zhejiang University, supervised by Prof. Zhaopeng Cui. I am actively seeking research opportunities. Feel free to email me if you would like to collaborate! / Email: zijuncui[at]uw[dot]edu / Github / LinkedIn / Calendar / |
|
|
|
|
|
|
Mingfei Chen*, Zijun Cui*, Xiulong Liu*, Jinlin Xiang, Caleb Zheng, Jingyuan Li, Eli Shlizerman Under review at NeurIPS 2025. webpage / demo / github / code We introduce SAVVY-Bench, the first benchmark for 3D spatial reasoning in dynamic audio-visual scenes. We also propose SAVVY, a novel training-free pipeline integrating egocentric spatial tracks and dynamic global maps, which significantly enhances AV-LLM performance for improved audio-visual spatial awareness in such environments. |
|
We propose PC-Planner, a physics-constrained self-supervised learning framework for robot motion planning in complex 3D environments. By introducing physical constraints and a novel shape-aware distance field (SADF), PC-Planner enables robust and efficient neural planning for robots with various shapes. Experiments in diverse settings show significant gains in success rate and planning time, outperforming classical and learning-based baselines. |
|
|
|
|