no code implementations • 1 Mar 2024 • Chuan Wen, Dinesh Jayaraman, Yang Gao
Spatial relationships between objects represent key scene information for humans to understand and interact with the world.
no code implementations • 21 Jan 2024 • Chengbo Yuan, Chuan Wen, Tong Zhang, Yang Gao
Our predicted flow offers actionable geometric and physics guidance, thus facilitating stable zero-shot skill transfer in real-world scenarios. We deploy our method with a policy based on closed-loop flow prediction.
no code implementations • 28 Dec 2023 • Chuan Wen, Xingyu Lin, John So, Kai Chen, Qi Dou, Yang Gao, Pieter Abbeel
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning.
no code implementations • 11 Oct 2023 • Yuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao
Nonetheless, we identify that tasks characterized by a progress dependency property pose significant challenges for such approaches; in these tasks, the agent needs to initially learn the expert's preceding behaviors before mastering the subsequent ones.
no code implementations • 27 Mar 2023 • Xianfan Gu, Chuan Wen, Weirui Ye, Jiaming Song, Yang Gao
Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals.
no code implementations • 18 Nov 2022 • Zekai Xu, Mingyi Zhang, Jiayue Hou, Xing Gong, Chuan Wen, Chengjie Wang, Junge Zhang
In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks.
1 code implementation • 1 Oct 2022 • Jiaye Teng, Chuan Wen, Dinghuai Zhang, Yoshua Bengio, Yang Gao, Yang Yuan
Conformal prediction is a distribution-free technique for establishing valid prediction intervals.
no code implementations • 20 Jul 2022 • Chia-Chi Chuang, Donglin Yang, Chuan Wen, Yang Gao
This is especially the case with image observations, where a single image only includes one view of the scene, and it suffers from a lack of motion information and object occlusions.
no code implementations • 22 Jun 2022 • Chuan Wen, Jianing Qian, Jierui Lin, Jiaye Teng, Dinesh Jayaraman, Yang Gao
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution.
no code implementations • 29 Sep 2021 • Chuan Wen, Jianing Qian, Jierui Lin, Dinesh Jayaraman, Yang Gao
When operating in partially observed settings, it is important for a control policy to fuse information from a history of observations.
no code implementations • 11 Jun 2021 • Chuan Wen, Jierui Lin, Jianing Qian, Yang Gao, Dinesh Jayaraman
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations.
no code implementations • NeurIPS 2020 • Chuan Wen, Jierui Lin, Trevor Darrell, Dinesh Jayaraman, Yang Gao
Imitation learning trains policies to map from input observations to the actions that an expert would choose.
no code implementations • 30 Apr 2019 • Chuan Wen, Jie Chang, Ya zhang, Siheng Chen, Yan-Feng Wang, Mei Han, Qi Tian
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.