ICLR

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Yanqiao Zhu, Jeehyun Hwang, Keir Adams, Zhen Liu, Bozhao Nan, Brock Stenfors, Yuanqi Du, Jatin Chauhan, Olaf Wiest, Olexandr Isayev, Connor W. Coley, Yizhou Sun, Wei Wang

Comments ICLR 2024

GIO: Gradient Information Optimization for Training Dataset Selection

Dante Everaert, Christopher Potts

Comments ICLR 2024 Spotlight paper

Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models

Dongzhuo Li

Comments ICLR 2023

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

Yoonyoung Cho, Junhyek Han, Yoontae Cho, Beomjoon Kim

Comments ICLR 2024

ActiveLab: Active Learning with Re-Labeling by Multiple Annotators

Hui Wen Goh, Jonas Mueller

Journal ref ICLR 2023 Workshop on Trustworthy ML

Adapting Large Language Models to Domains via Reading Comprehension

Daixuan Cheng, Shaohan Huang, Furu Wei

Comments ICLR 2024 Conference

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, Ping Luo

Comments Published in ICLR 2024

Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

Ali Hummos

Comments Published ICLR 2023

Journal ref The Eleventh International Conference on Learning Representations 2023

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Miltiadis Kofinas, Boris Knyazev, Yan Zhang, Yunlu Chen, Gertjan J. Burghouts, Efstratios Gavves, Cees G. M. Snoek, David W. Zhang

Comments In ICLR 2024. Source code: https://github.com/mkofinas/neural-graphs

Enhancing Neural Training via a Correlated Dynamics Model

Jonathan Brokman, Roy Betser, Rotem Turjeman, Tom Berkov, Ido Cohen, Guy Gilboa

Comments ICLR 2024 accepted URL: https://openreview.net/forum?id=c9xsaASm9L

First-order ANIL provably learns representations despite overparametrization

Oğuz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion

Comments 42 pages, 17 figures

Journal ref O. K. Yüksel, E. Boursier and N. Flammarion, "First-order ANIL provably learns representations despite overparametrisation", in The Twelfth International Conference on Learning Representations, 2024

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery

Linan Yue, Qi Liu, Yichao Du, Li Wang, Weibo Gao, Yanqing An

Comments Accepted to ICLR 2024

Robust agents learn causal world models

Jonathan Richens, Tom Everitt

Comments ICLR 2024 (oral). Updated agents section, new corollary

The Silent Curriculum: How Does LLM Monoculture Shape Educational Content and Its Accessibility?

Aman Priyanshu, Supriti Vijay

Comments 5 pages and 4 figures. Accepted at The Workshop on Global AI Cultures at the International Conference on Learning Representations, 2024 (ICLR'24)

PTaRL: Prototype-based Tabular Representation Learning via Space Calibration

Hangting Ye, Wei Fan, Xiaozhuang Song, Shun Zheng, He Zhao, Dandan Guo, Yi Chang

Comments Accepted by ICLR 2024

Deep Learning on Object-centric 3D Neural Fields

Pierluigi Zama Ramirez, Luca De Luigi, Daniele Sirocchi, Adriano Cardace, Riccardo Spezialetti, Francesco Ballerini, Samuele Salti, Luigi Di Stefano

Comments Extended version of the paper "Deep Learning on Implicit Neural Representations of Shapes" that was presented at ICLR 2023. Accepted at TPAMI. arXiv admin note: text overlap with arXiv:2302.05438

Spurious Feature Diversification Improves Out-of-distribution Generalization

Yong Lin, Lu Tan, Yifan Hao, Honam Wong, Hanze Dong, Weizhong Zhang, Yujiu Yang, Tong Zhang

Comments ICLR 2024

One for All: Towards Training One Graph Model for All Classification Tasks

Hao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen, Muhan Zhang

Comments 23 Pages, Published at ICLR 2024

Conformal Inductive Graph Neural Networks

Soroush H. Zargarbashi, Aleksandar Bojchevski

Comments Published as a conference paper at ICLR 2024

On the Role of Discrete Tokenization in Visual Representation Learning

Tianqi Du, Yifei Wang, Yisen Wang

Comments ICLR 2024 Spotlight

Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag

Lukas S. Huber, Fred W. Mast, Felix A. Wichmann

Comments Final version accepted @ ICLR 2024 Workshop on Representational Alignment (Re-Align)

On the Foundations of Shortcut Learning

Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael C. Mozer

Comments ICLR 2024

Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models

Zijun Wu, Yongkang Wu, Lili Mou

Comments Accepted by ICLR 2024

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu

Comments 31 pages, 7 tables, 6 figures. In ICLR 2024

How Aligned are Different Alignment Metrics?

Jannis Ahlert, Thomas Klein, Felix Wichmann, Robert Geirhos

Comments submitted to the ICLR 2024 Workshop on Representational Alignment (Re-Align)

Lie Group Decompositions for Equivariant Neural Networks

Mircea Mironenco, Patrick Forré

Comments Published at ICLR 2024. Code is available at https://github.com/mirceamironenco/rgenn

AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference

Xuanlei Zhao, Shenggan Cheng, Guangyang Lu, Jiarui Fang, Haotian Zhou, Bin Jia, Ziming Liu, Yang You

Comments ICLR 2024

Less is More: Discovering Concise Network Explanations

Neehar Kondapaneni, Markus Marks, Oisin Mac Aodha, Pietro Perona

Comments 9 pages, 5 figures; ICLR Re-Align Workshop 2024; Project Page: https://www.vision.caltech.edu/dcne/ Github: https://github.com/nkondapa/DiscoveringConciseNetworkExplanations

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

Lukas Struppek, Dominik Hintersdorf, Kristian Kersting

Comments Published as a conference paper at ICLR 2024

Augmented Bayesian Policy Search

Mahdi Kallel, Debabrota Basu, Riad Akrour, Carlo D'Eramo

Comments Accepted to the International Conference on Learning Representations (ICLR) 2024