ICLR

Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML

Robin van de Water, Hendrik Schmidt, Paul Elbers, Patrick Thoral, Bert Arnrich, Patrick Rockenschaub

Comments Main benchmark: https://github.com/rvandewater/YAIB, Cohort generation: https://github.com/rvandewater/YAIB-cohorts, Models: https://github.com/rvandewater/YAIB-models. To be published in ICLR 2024 proceedings

Equivariant amortized inference of poses for cryo-EM

Larissa de Ruijter, Gabriele Cesa

Comments Published at the GEM workshop, ICLR 2024

Contextualized Diffusion Models for Text-Guided Image and Video Generation

Ling Yang, Zhilong Zhang, Zhaochen Yu, Jingwei Liu, Minkai Xu, Stefano Ermon, Bin Cui

Comments ICLR 2024. Project: https://github.com/YangLing0818/ContextDiff

Neural Common Neighbor with Completion for Link Prediction

Xiyuan Wang, Haotong Yang, Muhan Zhang

Comments ICLR 2024

Attention-based Iterative Decomposition for Tensor Product Representation

Taewon Park, Inchul Choi, Minho Lee

Comments Published in ICLR 2024

Solar Panel Segmentation :Self-Supervised Learning Solutions for Imperfect Datasets

Sankarshanaa Sagaram, Krish Didwania, Laven Srivastava, Aditya Kasliwal, Pallavi Kailas, Ujjwal Verma

Comments Published at ICLR Tiny Paper 2024

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates

Siqi Zhang, Sayantan Choudhury, Sebastian U Stich, Nicolas Loizou

Comments ICLR 2024

ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering

Ilya Shenbin, Sergey Nikolenko

Comments Published as a conference paper at ICLR 2024; authors' version

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack

Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR 2024). Code is available at https://brusliattack.github.io/

Conformal Language Modeling

Victor Quach, Adam Fisch, Tal Schuster, Adam Yala, Jae Ho Sohn, Tommi S. Jaakkola, Regina Barzilay

Comments ICLR 2024

Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

Yeongwoo Song, Hawoong Jeong

Comments Conference paper at ICLR 2024

Simplifying Transformer Blocks

Bobby He, Thomas Hofmann

Comments ICLR 2024

Hypothesis Search: Inductive Reasoning with Language Models

Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman

Comments ICLR 2024. The first two authors contributed equally. Code: https://github.com/Relento/hypothesis_search

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, RJ Skerry-Ryan, Michelle Tadmor Ramanovich

Comments ICLR 2024 camera-ready

Modally Reduced Representation Learning of Multi-Lead ECG Signals through Simultaneous Alignment and Reconstruction

Nabil Ibtehaz, Masood Mortazavi

Comments Accepted as a Workshop Paper at TS4H@ICLR2024

Journal ref ICLR 2024 Workshop on Learning from Time Series For Health

Luganda Speech Intent Recognition for IoT Applications

Andrew Katumba, Sudi Murindanyi, John Trevor Kasule, Elvis Mugume

Comments Presented as a conference paper at ICLR 2024/AfricaNLP

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning

Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov

Comments Accepted at Twelfth International Conference on Learning Representations (ICLR 2024)

Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Pablo Pernias, Dominic Rampas, Mats L. Richter, Christopher J. Pal, Marc Aubreville

Comments Corresponding to "Würstchen v2"

Journal ref The Twelfth International Conference on Learning Representations (ICLR), 2024

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts

Ruipeng Zhang, Ziqing Fan, Jiangchao Yao, Ya Zhang, Yanfeng Wang

Comments Published as a conference paper at ICLR 2024

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

Haanvid Lee, Tri Wahyu Guntara, Jongmin Lee, Yung-Kyun Noh, Kee-Eung Kim

Comments 23 pages, 2 figures, Accepted at ICLR 2024 (spotlight)

Debiasing Algorithm through Model Adaptation

Tomasz Limisiewicz, David Mareček, Tomáš Musil

Comments Accepted to ICLR 2024

ViTGAN: Training GANs with Vision Transformers

Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, Ce Liu

Comments Accepted to ICLR 2022 (Spotlight)

On the Saturation Effect of Kernel Ridge Regression

Yicheng Li, Haobo Zhang, Qian Lin

Comments ICLR 2023; Minor errors are corrected in this version

Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment

Tengjun Huang

Comments Accepted by the Twelfth International Conference on Learning Representations (ICLR) Workshop

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, Dacheng Tao

Comments International Conference on Learning Representations (ICLR 2024)

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

Emmeran Johnson, Ciara Pike-Burke, Patrick Rebeschini

Comments Accepted at ICLR 2024

Predicting Classification Accuracy When Adding New Unobserved Classes

Yuli Slavutsky, Yuval Benjamini

Journal ref International Conference on Learning Representations (ICLR), 2021

Pre-training with Synthetic Data Helps Offline Reinforcement Learning

Zecheng Wang, Che Wang, Zixuan Dong, Keith Ross

Comments 37 pages, 17 figures; Published at ICLR 2024; Code: https://github.com/Victor-wang-902/synthetic-pretrain-rl

From Sparse to Soft Mixtures of Experts

Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Neil Houlsby

Comments Published as a conference paper at ICLR 2024

A CMDP-within-online framework for Meta-Safe Reinforcement Learning

Vanshaj Khattar, Yuhao Ding, Bilgehan Sel, Javad Lavaei, Ming Jin

Journal ref ICLR 2023