ICLR

Strengthening Subcommunities: Towards Sustainable Growth in AI Research

Andi Peng, Jessica Zosa Forde, Yonadav Shavit, Jonathan Frankle

Comments ICLR 2022 ML Evaluation Standards Workshop

Non-Parallel Text Style Transfer with Self-Parallel Supervision

Ruibo Liu, Chongyang Gao, Chenyan Jia, Guangxuan Xu, Soroush Vosoughi

Comments In ICLR 2022

An Extendable, Efficient and Effective Transformer-based Object Detector

Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang

Comments An extension of the ICLR paper, ViDT: An Efficient and Effective Fully Transformer-based Object Detector. arXiv admin note: substantial text overlap with arXiv:2110.03921

Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar

Yaojie Hu, Xingjian Shi, Qiang Zhou, Lee Pike

Comments ICLR 2022 Deep Learning for Code workshop

Rethinking Machine Learning Model Evaluation in Pathology

Syed Ashar Javed, Dinkar Juyal, Zahil Shanis, Shreya Chakraborty, Harsha Pokkalla, Aaditya Prakash

Comments ICLR 2022 ML Evaluation Workshop

Natural Language Descriptions of Deep Visual Features

Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, Jacob Andreas

Comments To be published as a conference paper at ICLR 2022

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

Andrea Dittadi, Frederik Träuble, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

Comments Published at ICLR 2022

Neural Structured Prediction for Inductive Node Classification

Meng Qu, Huiyu Cai, Jian Tang

Comments iclr 2022

Separating the World and Ego Models for Self-Driving

Vlad Sobal, Alfredo Canziani, Nicolas Carion, Kyunghyun Cho, Yann LeCun

Comments 8 pages main content, 14 with references and appendix. 5 figures in total. Submitted and accepted to ICLR 2022 workshop on Generalizable Policy Learning in the Physical World (https://ai-workshops.github.io/generalizable-policy-learning-in-the-physical-world/)

Accelerated Policy Learning with Parallel Differentiable Simulation

Jie Xu, Viktor Makoviychuk, Yashraj Narang, Fabio Ramos, Wojciech Matusik, Animesh Garg, Miles Macklin

Comments International Conference on Learning Representations

Global Counterfactual Explanations: Investigations, Implementations and Improvements

Dan Ley, Saumitra Mishra, Daniele Magazzeni

Comments Published as a workshop paper at ICLR 2022 (5 page main text, references, 3 page appendix)

Towards Self-Supervised Learning of Global and Object-Centric Representations

Federico Baldassarre, Hossein Azizpour

Comments Published at the ICLR 2022 workshop on Objects, Structure and Causality. Code, datasets, and notebooks are available at https://github.com/baldassarreFe/iclr-osc-22

Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Youwei Liang, Chongjian Ge, Zhan Tong, Yibing Song, Jue Wang, Pengtao Xie

Comments ICLR 2022 Spotlight

Open-Set Recognition: a Good Closed-Set Classifier is All You Need?

Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

Comments ICLR 22 Oral. Changes from pre-print highlighted on Github page

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning

Ugo Lecerf, Christelle Yemdji-Tchassi, Pietro Michiardi

Comments To appear in Generalizable Policy Learning in the Physical World workshop (ICLR 2022)

Distributionally Robust Models with Parametric Likelihood Ratios

Paul Michel, Tatsunori Hashimoto, Graham Neubig

Comments ICLR 2022

Document Structure aware Relational Graph Convolutional Networks for Ontology Population

Abhay M Shalghar, Ayush Kumar, Balaji Ganesan, Aswin Kannan, Akshay Parekh, Shobha G

Comments 8 pages single column, 5 figures. DLG4NLP Workshop at ICLR 2022

Surrogate Ensemble Forecasting for Dynamic Climate Impact Models

Julian Kuehnert, Deborah McGlynn, Sekou L. Remy, Aisha Walcott-Bryant, Anne Jones

Comments Published as a workshop paper at ICLR 2022: https://pml4dc.github.io/iclr2022/papers.html

When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine

Comments ICLR 2022. First two authors contributed equally

Anti-Concentrated Confidence Bonuses for Scalable Exploration

Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade

Journal ref International Conference on Learning Representations 2022

Convolutional autoencoders for spatially-informed ensemble post-processing

Sebastian Lerch, Kai L. Polsterer

Comments Accepted as conference paper at ICLR 2022 - AI for Earth and Space Science Workshop, https://ai4earthscience.github.io/iclr-2022-workshop/

How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision

Dongkwan Kim, Alice Oh

Comments ICLR 2021

Information-theoretic Online Memory Selection for Continual Learning

Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis Titsias

Comments ICLR 2022

LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models

Santiago Ontanon, Joshua Ainslie, Vaclav Cvicek, Zachary Fisher

Comments Accepted at ICLR 2022 OSC workshop (v3 contains updated results after fixing a problem in dataset generation)

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

Anuroop Sriram, Abhishek Das, Brandon M. Wood, Siddharth Goyal, C. Lawrence Zitnick

Comments ICLR 2022

Learning to Guide and to Be Guided in the Architect-Builder Problem

Paul Barde, Tristan Karch, Derek Nowrouzezahrai, Clément Moulin-Frier, Christopher Pal, Pierre-Yves Oudeyer

Comments International Conference on Learning Representations (2022)

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

Yandong Wen, Weiyang Liu, Adrian Weller, Bhiksha Raj, Rita Singh

Comments ICLR 2022 Spotlight (v3: Updated Appendix)

Fair Machine Learning under Limited Demographically Labeled Data

Mustafa Safa Ozdayi, Murat Kantarcioglu, Rishabh Iyer

Comments Will appear at ICLR 2022 Socially Responsible Machine Learning (SRML) Workshop

VAE Approximation Error: ELBO and Exponential Families

Alexander Shekhovtsov, Dmitrij Schlesinger, Boris Flach

Comments ICLR 2022 spotlight

Neural networks with late-phase weights

Johannes von Oswald, Seijin Kobayashi, Alexander Meulemans, Christian Henning, Benjamin F. Grewe, João Sacramento

Comments 25 pages, 6 figures

Journal ref Published as a conference paper at ICLR 2021