ICLR

Leveraging Large Language Models for Multiple Choice Question Answering

Joshua Robinson, Christopher Michael Rytting, David Wingate

Comments Accepted for ICLR 2023

Treeformer: Dense Gradient Trees for Efficient Attention Computation

Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain

Comments ICLR 2023

Easy Differentially Private Linear Regression

Kareem Amin, Matthew Joseph, Mónica Ribero, Sergei Vassilvitskii

Comments This version corresponds to the camera-ready at ICLR 2023

SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments

Tsun-Hsuan Wang, Pingchuan Ma, Andrew Everett Spielberg, Zhou Xian, Hao Zhang, Joshua B. Tenenbaum, Daniela Rus, Chuang Gan

Comments ICLR 2023. Project page: https://sites.google.com/view/softzoo-iclr-2023

Effectively Modeling Time Series with Simple Discrete State Spaces

Michael Zhang, Khaled K. Saab, Michael Poli, Tri Dao, Karan Goel, Christopher Ré

Comments 45 pages, 8 figures, 20 tables, ICLR 2023

Identifiability Results for Multimodal Contrastive Learning

Imant Daunhawer, Alice Bizeul, Emanuele Palumbo, Alexander Marx, Julia E. Vogt

Comments ICLR 2023 camera-ready version

Learning Vortex Dynamics for Fluid Inference and Prediction

Yitong Deng, Hong-Xing Yu, Jiajun Wu, Bo Zhu

Comments ICLR 2023, project webpage: https://yitongdeng.github.io/vortex_learning_webpage/

Human-Guided Fair Classification for Natural Language Processing

Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin Vechev

Comments Published at ICLR 2023 (notable top 25%). 30 pages, 1 figure

Sampling-based inference for large linear models, with application to linearised Laplace

Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric Nalisnick, David Janz, José Miguel Hernández-Lobato

Comments Published at ICLR 2023. This latest Arxiv version is extended with a demonstration of the proposed methods on the Imagenet dataset

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A. Erdogdu

Comments 39 pages, 2 figures. To appear in the International Conference on Learning Representations (ICLR), 2023

Corrupted Image Modeling for Self-Supervised Visual Pre-Training

Yuxin Fang, Li Dong, Hangbo Bao, Xinggang Wang, Furu Wei

Comments ICLR 2023

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

Hao Chen, Ran Tao, Yue Fan, Yidong Wang, Jindong Wang, Bernt Schiele, Xing Xie, Bhiksha Raj, Marios Savvides

Comments Accepted by ICLR 2023

ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces

Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Qiuyi Zhang, Daiyi Peng, Deepali Jain, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Yuxiang Yang

Comments Previously published at ICLR 2020 NAS Workshop. See https://github.com/google-research/google-research/tree/master/es_enas for associated code

Is forgetting less a good inductive bias for forward transfer?

Jiefeng Chen, Timothy Nguyen, Dilan Gorur, Arslan Chaudhry

Comments Published as a conference paper at ICLR 2023

Journal ref ICLR 2023

Masked Vision and Language Modeling for Multi-modal Representation Learning

Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas, Rahul Bhotika, Stefano Soatto

Comments International Conference on Learning Representations (ICLR) 2023

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

Yichen Qian, Ming Lin, Xiuyu Sun, Zhiyu Tan, Rong Jin

Comments Accepted at ICLR 2022 for poster. Camera ready version

Journal ref International Conference on Learning Representations (2022)

Learning Accurate Entropy Model with Global Reference for Image Compression

Yichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Hao Li, Rong Jin

Journal ref International Conference on Learning Representations (2021)

AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks

Kaidi Cao, Jiaxuan You, Jiaju Liu, Jure Leskovec

Comments ICLR 2023

Relational Multi-Task Learning: Modeling Relations between Data and Tasks

Kaidi Cao, Jiaxuan You, Jure Leskovec

Comments ICLR 2022 Spotlight

Invertible mapping between fields in CAMELS

Sambatra Andrianomena, Sultan Hassan, Francisco Villaescusa-Navarro

Comments 5 pages, 3 figures, Accepted at the ICLR 2023 Workshop on Physics for Machine Learning (Camera-ready version)

A law of adversarial risk, interpolation, and label noise

Daniel Paleka, Amartya Sanyal

Comments 22 pages, 8 figures. Accepted for ICLR 2023

Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos

David Fan, Deyu Yang, Xinyu Li, Vimal Bhat, Rohith MV

Comments Accepted to the ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models

Random Laplacian Features for Learning with Hyperbolic Space

Tao Yu, Christopher De Sa

Comments ICLR 2023

Transformer-based World Models Are Happy With 100k Interactions

Jan Robine, Marc Höftmann, Tobias Uelwer, Stefan Harmeling

Comments Published as a conference paper at ICLR 2023. Code is available at https://github.com/jrobine/twm

A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data

Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet

Comments Accepted by ICLR 2023

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

Luca Franco, Paolo Mandica, Bharti Munjal, Fabio Galasso

Comments Accepted at ICLR 2023

Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation

Ziqi Wang, Yuexin Wu, Frederick Liu, Daogao Liu, Le Hou, Hongkun Yu, Jing Li, Heng Ji

Comments 20 pages, 5 figures. Accepted by ICLR 2023

Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient

Yuda Song, Yifei Zhou, Ayush Sekhari, J. Andrew Bagnell, Akshay Krishnamurthy, Wen Sun

Comments 42 pages, 6 figures. Published at ICLR 2023. Code available at https://github.com/yudasong/HyQ

Relational Attention: Generalizing Transformers for Graph-Structured Tasks

Cameron Diao, Ricky Loynd

Comments The Eleventh International Conference on Learning Representations, ICLR'23

The Surprising Computational Power of Nondeterministic Stack RNNs

Brian DuSell, David Chiang

Comments 21 pages, 8 figures. Published at ICLR 2023