ICLR

metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models

Alex Kipnis, Konstantinos Voudouris, Luca M. Schulze Buschoff, Eric Schulz

Comments accepted for publication at ICLR 2025

Text-to-Image Rectified Flow as Plug-and-Play Priors

Xiaofeng Yang, Cheng Chen, Xulei Yang, Fayao Liu, Guosheng Lin

Comments ICLR 2025 Camera Ready. Code: https://github.com/yangxiaofeng/rectified_flow_prior

Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?

Boshen Xu, Ziheng Wang, Yang Du, Zhinan Song, Sipeng Zheng, Qin Jin

Comments Accepted by ICLR 2025. Code: https://github.com/xuboshen/EgoNCEpp

eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels

Alexander DeRieux, Walid Saad

Comments Published in ICLR 2025, 32 pages, 17 figures

SpinQuant: LLM quantization with learned rotations

Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort

Comments ICLR 2025

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It

Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis

Comments Published as a conference paper at ICLR 2025

Stochastic Gradient Descent for Gaussian Processes Done Right

Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz

Journal ref International Conference on Learning Representations, 2024

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari

Comments 10 pages, ICLR 2025 conference

Accelerating Diffusion Transformers with Token-wise Feature Caching

Chang Zou, Xuyang Liu, Ting Liu, Siteng Huang, Linfeng Zhang

Comments ToCa is honored to be accepted by ICLR 2025

Theory on Mixture-of-Experts in Continual Learning

Hongbo Li, Sen Lin, Lingjie Duan, Yingbin Liang, Ness B. Shroff

Comments This paper has been accepted by ICLR 2025 (Spotlight)

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels

Hyeonsu Jeong, Hye Won Chung

Comments ICLR 2025

FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise

Yunlong Yuan, Yuanfan Guo, Chunwei Wang, Wei Zhang, Hang Xu, Li Zhang

Comments ICLR 2025

Bridging the Data Provenance Gap Across Text, Speech and Video

Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Naana Obeng-Marnu, Manan Dey, Mohammed Hamdy, Nayan Saxena, Ahmad Mustafa Anis, Emad A. Alghamdi, Vu Minh Chien, Da Yin, Kun Qian, Yizhi Li, Minnie Liang, An Dinh, Shrestha Mohanty, Deividas Mataciunas, Tobin South, Jianguo Zhang, Ariel N. Lee, Campbell S. Lund, Christopher Klamm, Damien Sileo, Diganta Misra, Enrico Shippole, Kevin Klyman, Lester JV Miranda, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Vipul Gupta, Vivek Sharma, Xuhui Zhou, Caiming Xiong, Luis Villa, Stella Biderman, Alex Pentland, Sara Hooker, Jad Kabbara

Comments ICLR 2025. 10 pages, 5 figures (main paper)

Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection

Guangsheng Bao, Yanbin Zhao, Juncai He, Yue Zhang

Comments ICLR 2025 camera version (10 pages, 9 figures, 9 tables)

Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning

Yang You, Yixin Li, Congyue Deng, Yue Wang, Leonidas Guibas

Comments 10 pages; Accepted to ICLR 2025

SMITE: Segment Me In TimE

Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki, Andrea Tagliasacchi, Ghassan Hamarneh, Ali Mahdavi Amiri

Comments ICLR 2025; Project page is at https://segment-me-in-time.github.io/

NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance

Raphael T. Husistein, Markus Reiher, Marco Eckhoff

Comments 21 pages, 9 figures, 13 tables

Journal ref 13th International Conference on Learning Representations, ICLR 2025, Singapore

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization

Xiaohua Feng, Yuyuan Li, Chaochao Chen, Li Zhang, Longfei Li, Jun Zhou, Xiaolin Zheng

Comments Accepted by ICLR 2025

How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark

Ruizhong Qiu, Weiliang Will Zeng, James Ezick, Christopher Lott, Hanghang Tong

Comments ICLR 2025

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Shicong Cen, Jincheng Mei, Katayoon Goshvadi, Hanjun Dai, Tong Yang, Sherry Yang, Dale Schuurmans, Yuejie Chi, Bo Dai

Comments ICLR 2025

Does Training with Synthetic Data Truly Protect Privacy?

Yunpeng Zhao, Jie Zhang

Comments Accepted to ICLR 2025

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

Tanqiu Jiang, Changjiang Li, Fenglong Ma, Ting Wang

Comments Published in ICLR 2025

Spiking Vision Transformer with Saccadic Attention

Shuai Wang, Malu Zhang, Dehao Zhang, Ammar Belatreche, Yichen Xiao, Yu Liang, Yimeng Shan, Qian Sun, Enqi Zhang, Yang Yang

Comments Published as a conference paper at ICLR 2025

Predicate Hierarchies Improve Few-Shot State Classification

Emily Jin, Joy Hsu, Jiajun Wu

Comments ICLR 2025. First two authors contributed equally. Project page: https://emilyzjin.github.io/projects/phier.html

UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

Ruifeng Li, Mingqian Li, Wei Liu, Yuhua Zhou, Xiangxin Zhou, Yuan Yao, Qiang Zhang, Hongyang Chen

Comments accepted as ICLR 2025 Spotlight

ScriptoriumWS: A Code Generation Assistant for Weak Supervision

Tzu-Heng Huang, Catherine Cao, Spencer Schoenberg, Harit Vishwakarma, Nicholas Roberts, Frederic Sala

Comments Appeared in ICLR'23 Deep Learning for Code (DL4C) Workshop & 2023 Midwest Machine Learning Symposium

Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning

Wei Wu, Can Liao, Zizhen Deng, Zhengrui Guo, Jinzhuo Wang

Comments Accepted by ICLR'2025

VLMaterial: Procedural Material Generation with Large Vision-Language Models

Beichen Li, Rundi Wu, Armando Solar-Lezama, Changxi Zheng, Liang Shi, Bernd Bickel, Wojciech Matusik

Comments ICLR 2025 Spotlight

TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling

Yury Gorishniy, Akim Kotelnikov, Artem Babenko

Comments ICLR 2025. Code: https://github.com/yandex-research/tabm

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

Jiacheng Ye, Jiahui Gao, Shansan Gong, Lin Zheng, Xin Jiang, Zhenguo Li, Lingpeng Kong

Comments ICLR 2025