ICLR

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

Jing Wang, Wonho Bae, Jiahong Chen, Kuangen Zhang, Leonid Sigal, Clarence W. de Silva

Comments ICLR 2025

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

Aldo Pareja, Nikhil Shivakumar Nayak, Hao Wang, Krishnateja Killamsetty, Shivchander Sudalairaj, Wenlong Zhao, Seungwook Han, Abhishek Bhandwaldar, Guangxuan Xu, Kai Xu, Ligong Han, Luke Inglis, Akash Srivastava

Comments 33 pages, 19 figures. Appendix included in submission. Submitted to ICLR 2025

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

Guangsheng Bao, Yanbin Zhao, Zhiyang Teng, Linyi Yang, Yue Zhang

Comments ICLR 2024 camera version (9 pages, 5 figures, 11 tables)

Physics-Inspired Interpretability Of Machine Learning Models

Maximilian P Niroomand, David J Wales

Comments 6 pages, 2 figures, ICLR 2023 Workshop on Physics for Machine Learning

Journal ref ICLR 2023 Workshop on Physics for Machine Learning

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra, Jayaraman J. Thiagarajan

Comments Published at ICLR 2024; Project page: https://pujacomputes.github.io/gduq/

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica, Vít Musil, Volodymyr Kuleshov, Georg Martius

Comments ICLR 2023 conference paper. The first two authors contributed equally

Journal ref The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023

Differentiation of Blackbox Combinatorial Solvers

Marin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolínek

Comments ICLR 2020 conference paper (spotlight). The first two authors contributed equally

Journal ref 8th International Conference on Learning Representations, ICLR 2020

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Sangyu Han, Yearim Kim, Nojun Kwak

Comments To be published in ICLR 2024

Video Decomposition Prior: A Methodology to Decompose Videos into Layers

Gaurav Shrivastava, Ser-Nam Lim, Abhinav Shrivastava

Comments Project Page - https://www.cs.umd.edu/~gauravsh/video_decomposition/index.html for video results. Extended version of ICLR publication

Radon Implicit Field Transform (RIFT): Learning Scenes from Radar Signals

Daqian Bao, Alex Saad-Falcon, Justin Romberg

Comments A version of this manuscript is under review for ICLR 2025. This updated manuscript correspond to the revisions during rebuttal phase

Grounding Language Plans in Demonstrations Through Counterfactual Perturbations

Yanwei Wang, Tsun-Hsuan Wang, Jiayuan Mao, Michael Hagenow, Julie Shah

Comments ICLR 2024 Spotlight

Journal ref In International Conference on Learning Representations (ICLR) (2024)

Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks

Edwin Zhang, Yujie Lu, Shinda Huang, William Wang, Amy Zhang

Comments ICLR 2024, Project and code available at https://github.com/ezhang7423/language-control-diffusion

Social-Transmotion: Promptable Human Trajectory Prediction

Saeed Saadatnejad, Yang Gao, Kaouther Messaoud, Alexandre Alahi

Comments ICLR 2024

SpaCE: The Spatial Confounding Environment

Mauricio Tec, Ana Trisovic, Michelle Audirac, Sophie Woodward, Jie Kate Hu, Naeem Khoshnevis, Francesca Dominici

Journal ref Published at ICLR 2024

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy

Comments ICLR 2024

Think Beyond Size: Adaptive Prompting for More Effective Reasoning

Kamesh R

Comments Submitted to ICLR 2025. This is a preprint version. Future revisions will include additional evaluations and refinements

Large-width functional asymptotics for deep Gaussian neural networks

Daniele Bracale, Stefano Favaro, Sandra Fortini, Stefano Peluchetti

Journal ref International Conference on Learning Representations (ICLR) 2021

U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fields

Vinayak Gupta, Manoj S, Mukund Varma T, Kaushik Mitra

Comments ICLR Tiny Papers 2024. arXiv admin note: text overlap with arXiv:2207.13298

Explaining Kernel Clustering via Decision Trees

Maximilian Fleissner, Leena Chennuru Vankadara, Debarghya Ghoshdastidar

Journal ref ICLR 2024

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Zeren Chen, Ziqin Wang, Zhen Wang, Huayang Liu, Zhenfei Yin, Si Liu, Lu Sheng, Wanli Ouyang, Yu Qiao, Jing Shao

Comments 22 pages, 12 figures. Accepted in ICLR 2024

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses

Andrew Lowy, Meisam Razaviyayn

Comments ICLR 2023

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Fei Shen, Hu Ye, Jun Zhang, Cong Wang, Xiao Han, Wei Yang

Comments Accepted to ICLR 2024. The final version is available at OpenReview: https://openreview.net/forum?id=rHzapPnCgT

Journal ref The Twelfth International Conference on Learning Representations, 2024

Select High-Level Features: Efficient Experts from a Hierarchical Classification Network

André Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop

Comments This two-page paper was accepted for a poster presentation at the 5th ICLR 2024 Workshop on Practical ML for Limited/Low Resource Settings (PML4LRS)

High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention

André Peter Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop

Comments Paper's findings on high-level parallelism and nested features directly contributes to 'Selecting High-Level Features: Efficient Experts from a Hierarchical Classification Network,' accepted at ICLR 2024's Practical ML for Low Resource Settings (PML4LRS) workshop (non-archival); a modified version has been accepted for presentation at the ICPR 2024

Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay

Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang

Comments 10 pages, 3 figures, 1 table, inclusion at ICLR 2024 Workshop on Generative Models for Decision Making

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez, Nicholas Botzer, David Vazquez, Christopher Pal, Marco Pedersoli, Issam Laradji

Comments ICLR 2024 Workshop on LLM Agents

Evaluating Representations with Readout Model Switching

Yazhe Li, Jorg Bornschein, Marcus Hutter

Journal ref International Conference on Learning Representations, 2023

Provable Compositional Generalization for Object-Centric Learning

Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel

Comments Oral at ICLR 2024. The first four authors contributed equally

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik Narasimhan

Comments Data, code, and leaderboard are available at https://www.swebench.com ICLR 2024, https://openreview.net/forum?id=VTF8yNQM66

Towards Establishing Guaranteed Error for Learned Database Operations

Sepanta Zeighami, Cyrus Shahabi

Comments Appeared in ICLR'24