Three Papers Accepted by NeurIPS 2026
🎉 Congratulations to our research team! We are thrilled to announce that three papers from our group have been accepted by the Conference on Neural Information Processing Systems (NeurIPS) 2026.
Featured Work
Our three accepted papers are:
Paper 1: PO-PDDL — Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
- Paper: Available on arXiv
- Project Page: PO-PDDL Project Website
Paper 2: I-Perceive — A Foundation Model for Vision-Language Active Perception
- Paper: Available on arXiv
- Project Page: I-Perceive Project Website
Paper 3: TGPO — Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation
- Paper: Available on arXiv
- Project Page: TGPO Project Website
We look forward to presenting our work and sharing our findings with the broader research community at NeurIPS 2026. Stay tuned for more details about the papers and presentations as we approach the conference!
Xuanjin Jin
Ph.D. student
My research interests include autonomous driving, planning under uncertainty, integrated planning and learning.
Yuan Liu
Undergraduate student
My research interests include robotics, robot manipulation, task planning under uncertainty
Renming Huang
Ph.D. student
My research interests include robotics, task planning and Reinforcement Learning
Zhuohang Wang
Undergraduate student
My research interests include robotic Active Perception and world action model
Chendong Zeng
Ph.D. student
My research interests include robotics, robot manipulation and robot learning.
Panpan Cai
Associate Professor
My research interests include robot motion planning, decision making, robot learning, parallel computing, and their applications to autonomous driving in crowded environments.