ICLR

What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions

Kiana Ehsani, Daniel Gordon, Thomas Nguyen, Roozbeh Mottaghi, Ali Farhadi

Comments Published as a conference paper at ICLR 2021

Dataset Condensation with Gradient Matching

Bo Zhao, Konda Reddy Mopuri, Hakan Bilen

Journal ref International Conference on Learning Representations 2021

IOT: Instance-wise Layer Reordering for Transformer Structures

Jinhua Zhu, Lijun Wu, Yingce Xia, Shufang Xie, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

Comments Accepted at ICLR-2021

Learning Structural Edits via Incremental Tree Transformations

Ziyu Yao, Frank F. Xu, Pengcheng Yin, Huan Sun, Graham Neubig

Comments ICLR 2021

WaNet -- Imperceptible Warping-based Backdoor Attack

Anh Nguyen, Anh Tran

Comments Accepted to ICLR 2021

MALI: A memory efficient and reverse accurate integrator for Neural ODEs

Juntang Zhuang, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan

Comments https://openreview.net/forum?id=blfSjHeFM_e

Journal ref International Conference on Learning Representation, ICLR 2021

Creative Sketch Generation

Songwei Ge, Vedanuj Goswami, C. Lawrence Zitnick, Devi Parikh

Comments Published as a conference paper at ICLR 2021

Text Generation by Learning from Demonstrations

Richard Yuanzhe Pang, He He

Comments ICLR 2021

BOIL: Towards Representation Change for Few-shot Learning

Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun

Comments 24 pages, 26 figures, 19 tables, ICLR 2021 published

Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability

Suraj Srinivas, Francois Fleuret

Comments Oral Presentation at ICLR 2021

Wasserstein Embedding for Graph Learning

Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann

Comments Final version to be presented at the Ninth International Conference on Learning Representations (ICLR 2021)

Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize

Nils Wandel, Michael Weinmann, Reinhard Klein

Comments to be published at International Conference on Learning Representations (ICLR) 2021

Robustness of classifiers to universal perturbations: a geometric perspective

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto

Comments Published at ICLR 2018

AdaSpeech: Adaptive Text to Speech for Custom Voice

Mingjian Chen, Xu Tan, Bohan Li, Yanqing Liu, Tao Qin, Sheng Zhao, Tie-Yan Liu

Comments Accepted by ICLR 2021

Usable Information and Evolution of Optimal Representations During Training

Michael Kleinman, Alessandro Achille, Daksh Idnani, Jonathan C. Kao

Comments ICLR 2021

Graph-Based Continual Learning

Binh Tang, David S. Matteson

Comments Published as a conference paper at ICLR 2021

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference

Sanghyun Hong, Yiğitcan Kaya, Ionuţ-Vlad Modoranu, Tudor Dumitraş

Comments Accepted to ICLR 2021 [Spotlight]; First two authors contributed equally

How to 0wn NAS in Your Spare Time

Sanghyun Hong, Michael Davinroy, Yiğitcan Kaya, Dana Dachman-Soled, Tudor Dumitraş

Comments Accepted to ICLR 2020 [Poster]; Our code is available at https://github.com/sanghyun-hong/How-to-0wn-NAS-in-Your-Spare-Time

Task-Agnostic Morphology Evolution

Donald J. Hejna, Pieter Abbeel, Lerrel Pinto

Comments ICLR 2021

Unlearnable Examples: Making Personal Data Unexploitable

Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang

Comments ICLR2021, In International Conference on Learning Representations

Learning Generalizable Visual Representations via Interactive Gameplay

Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M Pratt, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, Ali Farhadi

Comments Replaced with version accepted to ICLR'21

Locally Free Weight Sharing for Network Width Search

Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu

Comments Accepted by ICLR 2021 Spotlight

Identifying Physical Law of Hamiltonian Systems via Meta-Learning

Seungjun Lee, Haesang Yang, Woojae Seong

Comments ICLR 2021

Anytime Sampling for Autoregressive Models via Ordered Autoencoding

Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon

Comments Accepted by ICLR 2021

Learning with AMIGo: Adversarially Motivated Intrinsic Goals

Andres Campero, Roberta Raileanu, Heinrich Küttler, Joshua B. Tenenbaum, Tim Rocktäschel, Edward Grefenstette

Comments 18 pages, 6 figures, published at The Ninth International Conference on Learning Representations (2021)

Understanding Knowledge Distillation in Non-autoregressive Machine Translation

Chunting Zhou, Graham Neubig, Jiatao Gu

Comments fix a typo; accepted by ICLR 2020

Return-Based Contrastive Representation Learning for Reinforcement Learning

Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu

Comments ICLR 2021

Neural Delay Differential Equations

Qunxi Zhu, Yao Guo, Wei Lin

Comments Accepted as a poster in ICLR 2021 (submitted 28 Sep 2020, revised 22 Nov 2020, accepted 08 Jan 2021)

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

Jiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li, Shu-Tao Xia

Comments Accepted by ICLR 2021

BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

Huanrui Yang, Lin Duan, Yiran Chen, Hai Li

Comments Published as a conference paper at ICLR 2021