发表论文

2024

SkillDiffuser: Interpretable hierarchical planning via skill abstractions in diffusion-based task execution

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR 2024)

PDF Code Project Page

SPET: Spatial-Temporal Tree Planning via Diffusion Models

International Conference on Learning Representations (ICLR 2024)

PDF Code Project Page

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

International Conference on Learning Representations (ICLR 2024)

PDF Code Project Page

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Models

International Conference on Learning Representations (ICLR 2024)

PDF Code Project Page

2023

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)

Spotlight
PDF Code Project Page

AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners

The Fortieth International Conference on Machine Learning (ICML 2023)

Oral Presentation
PDF Code Project Page

MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL

The Fortieth International Conference on Machine Learning (ICML 2023)

PDF Code Project Page

EC^2: Emergent Communication for Embodied Control

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR 2023)

PDF Code Project Page

CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving

Eleventh International Conference on Learning Representations (ICLR 2023)

PDF Code Project Page

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

Eleventh International Conference on Learning Representations (ICLR 2023)

PDF Code Project Page

2022

DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

The 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Spotlight
PDF Code Project Page

CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer

The 39th International Conference on Machine Learning (ICML 2022)

PDF Code Project Page