1 code implementation • 1 Nov 2023 • Zhan Ling, Yunhao Fang, Xuanlin Li, Tongzhou Mu, Mingu Lee, Reza Pourreza, Roland Memisevic, Hao Su
Large Language Models (LLMs) have achieved tremendous progress, yet they still often struggle with challenging reasoning problems.
no code implementations • 20 Jul 2023 • Zhiao Huang, Litian Liang, Zhan Ling, Xuanlin Li, Chuang Gan, Hao Su
We then present a practical model-based RL method, called Reparameterized Policy Gradient (RPG), which leverages the multimodal policy parameterization and learned world model to achieve strong exploration capabilities and high data efficiency.
1 code implementation • ICCV 2023 • Xuanlin Li, Yunhao Fang, Minghua Liu, Zhan Ling, Zhuowen Tu, Hao Su
Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution.
1 code implementation • 11 Jun 2023 • Zhan Ling, Yunchao Yao, Xuanlin Li, Hao Su
Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations.
1 code implementation • NeurIPS 2023 • Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, Hao Su
In light of this, we propose to decompose a reasoning verification process into a series of step-by-step subprocesses, each only receiving their necessary context and premises.
1 code implementation • 9 Feb 2023 • Jiayuan Gu, Fanbo Xiang, Xuanlin Li, Zhan Ling, Xiqiang Liu, Tongzhou Mu, Yihe Tang, Stone Tao, Xinyue Wei, Yunchao Yao, Xiaodi Yuan, Pengwei Xie, Zhiao Huang, Rui Chen, Hao Su
Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI.
2 code implementations • CVPR 2023 • Minghua Liu, Yinhao Zhu, Hong Cai, Shizhong Han, Zhan Ling, Fatih Porikli, Hao Su
Generalizable 3D part segmentation is important but challenging in vision and robotics.
1 code implementation • 14 Oct 2022 • Minghua Liu, Xuanlin Li, Zhan Ling, Yangyan Li, Hao Su
We study how choices of input point cloud coordinate frames impact learning of manipulation skills from 3D point clouds.
1 code implementation • 26 Jun 2022 • Zhiwei Jia, Xuanlin Li, Zhan Ling, Shuang Liu, Yiran Wu, Hao Su
Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations.
1 code implementation • 5 May 2022 • Xinyue Wei, Minghua Liu, Zhan Ling, Hao Su
Approximate convex decomposition aims to decompose a 3D shape into a set of almost convex components, whose convex hulls can then be used to represent the input shape.
3 code implementations • 30 Jul 2021 • Tongzhou Mu, Zhan Ling, Fanbo Xiang, Derek Yang, Xuanlin Li, Stone Tao, Zhiao Huang, Zhiwei Jia, Hao Su
Here we propose SAPIEN Manipulation Skill Benchmark (ManiSkill) to benchmark manipulation skills over diverse objects in a full-physics simulator.
no code implementations • ICLR 2020 • Fangchen Liu, Zhan Ling, Tongzhou Mu, Hao Su
Consider an imitation learning problem that the imitator and the expert have different dynamics models.