Chao Zhang 张超

I am currently a Ph.D. student in Computer Science at Nanjing University. My research focuses on embodied intelligence, including VLA, code-as-policy, VLN, and self-evolution, aiming at reliable, closed-loop self-evolving physical intelligence. Previously, I worked on end-to-end prediction and planning for autonomous driving at Xiaomi.

Publications

Ding, X., Mi, L., Huang, M., Wang, Z., Zhang, C., et al. Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence. arXiv:2608.16590, 2026.
Ji, Z., Zhang, C., Huang, J., Li, S., Li, X., Li, Z. Few-Shot Object Detection via Conditional Variational Adaptive Memory Enhancement. ICASSP 2026.
Zhang, C. ExtremeFormer: a new framework for accurate object tracking by designing an efficient head prediction module. The Visual Computer, 2023.
Zhang, C. Block-Matching Multi-pedestrian Tracking. ICONIP 2023 (Oral).

Chao Zhang张超

Publications