Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Chuang Gan

Certifiably Robust Interpretation via Renyi Differential Privacy


Jul 04, 2021
Ao Liu, Xiaoyu Chen, Sijia Liu, Lirong Xia, Chuang Gan

* 19 page main text + appendix 

  Access Paper or Ask Questions

Global Rhythm Style Transfer Without Text Transcriptions


Jun 16, 2021
Kaizhi Qian, Yang Zhang, Shiyu Chang, Jinjun Xiong, Chuang Gan, David Cox, Mark Hasegawa-Johnson


  Access Paper or Ask Questions

Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning


Jun 13, 2021
Shaobo Min, Qi Dai, Hongtao Xie, Chuang Gan, Yongdong Zhang, Jingdong Wang


  Access Paper or Ask Questions

Adversarial Option-Aware Hierarchical Imitation Learning


Jun 11, 2021
Mingxuan Jing, Wenbing Huang, Fuchun Sun, Xiaojian Ma, Tao Kong, Chuang Gan, Lei Li

* accepted by ICML 2021 

  Access Paper or Ask Questions

Temporal and Object Quantification Networks


Jun 10, 2021
Jiayuan Mao, Zhezheng Luo, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu, Leslie Pack Kaelbling, Tomer D. Ullman

* IJCAI 2021. First two authors contributed equally. Project page: http://toqnet.csail.mit.edu/ 

  Access Paper or Ask Questions

Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules


May 11, 2021
Aisha Urooj Khan, Hilde Kuehne, Kevin Duarte, Chuang Gan, Niels Lobo, Mubarak Shah

* IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 

  Access Paper or Ask Questions

Curious Representation Learning for Embodied Intelligence


May 03, 2021
Yilun Du, Chuang Gan, Phillip Isola


  Access Paper or Ask Questions

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics


Apr 07, 2021
Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan

* Accepted to ICLR 2021 as a spotlight presentation. Project page: http://plasticinelab.csail.mit.edu/ 

  Access Paper or Ask Questions

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning


Mar 30, 2021
Zhenfang Chen, Jiayuan Mao, Jiajun Wu, Kwan-Yee Kenneth Wong, Joshua B. Tenenbaum, Chuang Gan

* ICLR 2021. Project page: http://dcl.csail.mit.edu/ 

  Access Paper or Ask Questions

TransCenter: Transformers with Dense Queries for Multiple-Object Tracking


Mar 28, 2021
Yihong Xu, Yutong Ban, Guillaume Delorme, Chuang Gan, Daniela Rus, Xavier Alameda-Pineda

* 16 pages, 9 figures 

  Access Paper or Ask Questions

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI


Mar 25, 2021
Chuang Gan, Siyuan Zhou, Jeremy Schwartz, Seth Alter, Abhishek Bhandwaldar, Dan Gutfreund, Daniel L. K. Yamins, James J DiCarlo, Josh McDermott, Antonio Torralba, Joshua B. Tenenbaum

* Project page: http://tdw-transport.csail.mit.edu/ 

  Access Paper or Ask Questions

Learning Task Decomposition with Ordered Memory Policy Network


Mar 19, 2021
Yuchen Lu, Yikang Shen, Siyuan Zhou, Aaron Courville, Joshua B. Tenenbaum, Chuang Gan


  Access Paper or Ask Questions

AGENT: A Benchmark for Core Psychological Reasoning


Feb 25, 2021
Tianmin Shu, Abhishek Bhandwaldar, Chuang Gan, Kevin A. Smith, Shari Liu, Dan Gutfreund, Elizabeth Spelke, Joshua B. Tenenbaum, Tomer D. Ullman

* 12 pages, 7 figures 

  Access Paper or Ask Questions

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning


Feb 20, 2021
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang


  Access Paper or Ask Questions

MVFNet: Multi-View Fusion Network for Efficient Video Recognition


Jan 05, 2021
Wenhao Wu, Dongliang He, Tianwei Lin, Fu Li, Chuang Gan, Errui Ding

* Accepted by AAAI2021 

  Access Paper or Ask Questions

Augmenting Policy Learning with Routines Discovered from a Demonstration


Dec 24, 2020
Zelin Zhao, Chuang Gan, Jiajun Wu, Xiaoxiao Guo, Joshua B. Tenenbaum

* To appear in AAAI-21. Code is available at https://github.com/sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL

  Access Paper or Ask Questions

Object-Centric Diagnosis of Visual Reasoning


Dec 21, 2020
Jianwei Yang, Jiayuan Mao, Jiajun Wu, Devi Parikh, David D. Cox, Joshua B. Tenenbaum, Chuang Gan


  Access Paper or Ask Questions

Synthetic Training for Monocular Human Mesh Recovery


Oct 27, 2020
Yu Sun, Qian Bao, Wu Liu, Wenpeng Gao, Yili Fu, Chuang Gan, Tao Mei


  Access Paper or Ask Questions

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning


Oct 05, 2020
Xiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan, Murray Campbell, Shiyu Chang

* Accepted to EMNLP 2020 

  Access Paper or Ask Questions

Location-aware Graph Convolutional Networks for Video Question Answering


Aug 07, 2020
Deng Huang, Peihao Chen, Runhao Zeng, Qing Du, Mingkui Tan, Chuang Gan


  Access Paper or Ask Questions

Tiny Transfer Learning: Towards Memory-Efficient On-Device Learning


Jul 28, 2020
Han Cai, Chuang Gan, Ligeng Zhu, Song Han


  Access Paper or Ask Questions

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events


Jul 27, 2020
Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba, Joshua B. Tenenbaum

* Project page: http://noisy-agent.csail.mit.edu 

  Access Paper or Ask Questions

Foley Music: Learning to Generate Music from Videos


Jul 21, 2020
Chuang Gan, Deng Huang, Peihao Chen, Joshua B. Tenenbaum, Antonio Torralba

* ECCV 2020. Project page: http://foley-music.csail.mit.edu 

  Access Paper or Ask Questions

MCUNet: Tiny Deep Learning on IoT Devices


Jul 20, 2020
Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, Song Han

* Demo video available here: https://youtu.be/YvioBgtec4U 

  Access Paper or Ask Questions

Generating Visually Aligned Sound from Videos


Jul 14, 2020
Peihao Chen, Yang Zhang, Mingkui Tan, Hongdong Xiao, Deng Huang, Chuang Gan

* Published in IEEE Transactions on Image Processing, 2020. Code, pre-trained models and demo video: https://github.com/PeihaoChen/regnet 

  Access Paper or Ask Questions

ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation


Jul 09, 2020
Chuang Gan, Jeremy Schwartz, Seth Alter, Martin Schrimpf, James Traer, Julian De Freitas, Jonas Kubilius, Abhishek Bhandwaldar, Nick Haber, Megumi Sano, Kuno Kim, Elias Wang, Damian Mrowca, Michael Lingelbach, Aidan Curtis, Kevin Feigelis, Daniel M. Bear, Dan Gutfreund, David Cox, James J. DiCarlo, Josh McDermott, Joshua B. Tenenbaum, Daniel L. K. Yamins

* Project page: http://www.threedworld.org 

  Access Paper or Ask Questions