Spatial Intelligence · Embodied Intelligence · Autonomous Systems
I am a tenured Associate Professor in the School of Computer Science and Technology at Tongji University. My research focuses on spatial and embodied intelligence, with memory mechanisms as a unifying theme.
Our work spans spatiotemporal reconstruction, foundation models, continual learning, reinforcement learning, safe decision-making, intelligent agents, and robotic systems. We study how memory helps these systems understand changing environments, learn from experience, and act safely over the long term.
Publications
Advances in Neural Information Processing Systems (NeurIPS 2025), 2025.
TL;DR: Introduces a mutual-learning place-recognition framework that jointly refines image descriptors and adaptive clusters to reduce supervision inconsistency from viewpoint changes and occlusion.
International Conference on Machine Learning (ICML 2025), 2025.
TL;DR: Models uncertainty in context representations and uses it to selectively gather task context for improved one-shot adaptation in offline meta-RL.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026, Denver, Colorado, 2026.
TL;DR: Proposes an uncertainty capture mechanism in generalizable NeRF for dynamic distractor scenes, enabling robust feedforward 3D reconstruction in such scenarios.
International Conference on Learning Representations (ICLR 2026), Rio de Janeiro, Brazil, 2026.
TL;DR: Identifies potentially optimal joint actions and adaptively adjusts training weights to improve convergence and policy recovery in cooperative multi-agent reinforcement learning.
International Conference on Learning Representations (ICLR 2026), Rio de Janeiro, Brazil, 2026.
TL;DR: Uses diffusion models to detect out-of-distribution actions and selectively regularize them while preserving beneficial actions.
Latest