ICLR

Online Preference Alignment for Language Models via Count-based Exploration

Chenjia Bai, Yang Zhang, Shuang Qiu, Qiaosheng Zhang, Kang Xu, Xuelong Li

Comments Accepted by ICLR 2025

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

Changlong Wu, Ananth Grama, Wojciech Szpankowski

Journal ref International Conference on Learning Representations (ICLR 2025). URL: https://openreview.net/pdf?id=OwNoTs2r8e

Order-aware Interactive Segmentation

Bin Wang, Anwesa Choudhuri, Meng Zheng, Zhongpai Gao, Benjamin Planche, Andong Deng, Qin Liu, Terrence Chen, Ulas Bagci, Ziyan Wu

Comments Accepted by ICLR 2025 Interactive demo can be found in project page: https://ukaukaaaa.github.io/projects/OIS/index.html

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

Binghui Li, Yuanzhi Li

Comments Published as a conference paper at ICLR 2025; 36 pages

On the expressiveness and spectral bias of KANs

Yixuan Wang, Jonathan W. Siegel, Ziming Liu, Thomas Y. Hou

Comments 20 pages, 7 figures

Journal ref ICLR 2025

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward

Yuzi Yan, Yibo Miao, Jialian Li, Yipin Zhang, Jian Xie, Zhijie Deng, Dong Yan

Journal ref ICLR 2025

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

Cong Lu, Shengran Hu, Jeff Clune

Comments Published as a conference paper at ICLR 2025

Learning Causal Alignment for Reliable Disease Diagnosis

Mingzhou Liu, Ching-Wen Lee, Xinwei Sun, Yu Qiao, Yizhou Wang

Comments ICLR-25

SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition

Qiang Wan, Zilong Huang, Jiachen Lu, Gang Yu, Li Zhang

Comments V4 is the ICLR 2023 conference version, and V6 is the IJCV 2025 version

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Marco Mistretta, Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, Andrew D. Bagdanov

Comments Accepted for publication at ICLR 2025

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

Jiate Li, Meng Pang, Yun Dong, Jinyuan Jia, Binghui Wang

Comments Accepted by ICLR 2025

Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning

Wesley A. Suttle, Aamodh Suresh, Carlos Nieto-Granda

Comments Accepted to ICLR 2025

M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model

Kehan Wen, Yutong Hu, Yao Mu, Lei Ke

Comments ICLR 2025

Ultra-Sparse Memory Network

Zihao Huang, Qiyang Min, Hongzhi Huang, Defa Zhu, Yutao Zeng, Ran Guo, Xun Zhou

Comments Published as a conference paper at ICLR 2025

BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation

Zhengrui Guo, Fangxu Zhou, Wei Wu, Qichen Sun, Lishuang Feng, Jinzhuo Wang, Hao Chen

Comments Accepted by ICLR'2025

A Unified Theory of Quantum Neural Network Loss Landscapes

Eric R. Anschuetz

Comments 60 pages, 3 figures, published version

Journal ref International Conference on Learning Representations (2025)

Model-agnostic meta-learners for estimating heterogeneous treatment effects over time

Dennis Frauen, Konstantin Hess, Stefan Feuerriegel

Comments Accepted at ICLR 2025

From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy

Julian Dörfler, Benito van der Zander, Markus Bläser, Maciej Liskiewicz

Comments accepted at ICLR 25

Hessian-Free Online Certified Unlearning

Xinbao Qiao, Meng Zhang, Ming Tang, Ermin Wei

Comments Accepted at ICLR 2025

Beyond Random Augmentations: Pretraining with Hard Views

Fabio Ferreira, Ivo Rapant, Jörg K. H. Franke, Frank Hutter

Journal ref The Thirteenth International Conference on Learning Representations (ICLR) 2025

Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount

Yanbiao Ma, Wei Dai, Jiayi Chen

Comments Published as a conference paper at ICLR 2025

Multi-Label Test-Time Adaptation with Bound Entropy Minimization

Xiangyu Wu, Feng Yu, Qing-Guo Chen, Yang Yang, Jianfeng Lu

Comments Accepted for publication at ICLR 2025; 17 pages; 3 figures

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

Khanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas

Comments ICLR 2025

What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models

Ahmed Imtiaz Humayun, Ibtihel Amara, Cristina Vasconcelos, Deepak Ramachandran, Candice Schumann, Junfeng He, Katherine Heller, Golnoosh Farnadi, Negar Rostamzadeh, Mohammad Havaei

Comments Accepted for publication at ICLR 2025

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

Chongjie Si, Xuehui Wang, Xue Yang, Zhengqin Xu, Qingyun Li, Jifeng Dai, Yu Qiao, Xiaokang Yang, Wei Shen

Comments 2025 ICLR

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

Jixun Yao, Hexin Liu, Chen Chen, Yuchen Hu, EngSiong Chng, Lei Xie

Comments Accepted by ICLR 2025

SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

Donglei Yu, Yang Zhao, Jie Zhu, Yangyifan Xu, Yu Zhou, Chengqing Zong

Comments Accepted to ICLR 2025. 23 pages,13 figures,11 tables

Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection

Hengzhuang Li, Teng Zhang

Comments ICLR 2025

PaPaGei: Open Foundation Models for Optical Physiological Signals

Arvind Pillai, Dimitris Spathis, Fahim Kawsar, Mohammad Malekzadeh

Comments Accepted at ICLR 2025. Improved version with new experiments and results. Code and models: https://github.com/nokia-bell-labs/papagei-foundation-model

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

Xinchen Zhang, Ling Yang, Guohao Li, Yaqi Cai, Jiake Xie, Yong Tang, Yujiu Yang, Mengdi Wang, Bin Cui

Comments ICLR 2025. Project: https://github.com/YangLing0818/IterComp