ICLR

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model

Wenhong Zhu, Zhiwei He, Xiaofeng Wang, Pengfei Liu, Rui Wang

Comments ICLR 2025(Spotlight)

LoLCATs: On Low-Rank Linearizing of Large Language Models

Michael Zhang, Simran Arora, Rahul Chalamala, Alan Wu, Benjamin Spector, Aaryan Singhal, Krithik Ramesh, Christopher Ré

Comments 58 pages, 25 figures, 26 tables, ICLR 2025

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li

Comments ICLR 2025, camera-ready version

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing

Feng Tian, Yixuan Li, Yichao Yan, Shanyan Guan, Yanhao Ge, Xiaokang Yang

Comments 31 pages

Journal ref ICLR 2025

Generative Flows on Synthetic Pathway for Drug Design

Seonghwan Seo, Minsu Kim, Tony Shen, Martin Ester, Jinkyoo Park, Sungsoo Ahn, Woo Youn Kim

Comments Accepted to ICLR 2025, 32 pages, 17 figures, code: https://github.com/SeonghwanSeo/RxnFlow

SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups

Yongxing Zhang, Donglin Yang, Renjie Liao

Comments ICLR 2025 Oral

SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

Kai Li, Wendi Sang, Chang Zeng, Runxuan Yang, Guo Chen, Xiaolin Hu

Comments Accepted by ICLR 2025

HelpSteer2-Preference: Complementing Ratings with Preferences

Zhilin Wang, Alexander Bukharin, Olivier Delalleau, Daniel Egert, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, Yi Dong

Comments Accepted to ICLR 2025; 28 pages, 3 figures

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord

Comments LLM-wrapper (v3) is published as a conference paper at ICLR 2025. (v1 was presented at EVAL-FoMo workshop, ECCV 2024.)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha

Comments Accepted to ICLR 2025. Project: https://sreyan88.github.io/VDGD/

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

Xinyi Shang, Peng Sun, Tao Lin

Comments https://github.com/LINs-lab/GIFT

Journal ref ICLR 2025

Can We Talk Models Into Seeing the World Differently?

Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, M. Jehanzeb Mirza, Margret Keuper, Janis Keuper

Comments Accepted at ICLR 2025

$σ$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples

Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo

Comments Paper accepted at International Conference on Learning Representations (ICLR 2025). Code available at https://github.com/sigma0-advx/sigma-zero

Indirect Gradient Matching for Adversarial Robust Distillation

Hongsin Lee, Seungju Cho, Changick Kim

Comments ICLR 2025

Differentially Private Learners for Heterogeneous Treatment Effects

Maresa Schröder, Valentyn Melnychuk, Stefan Feuerriegel

Comments Published at ICLR 2025

Advantage-Guided Distillation for Preference Alignment in Small Language Models

Shiping Gao, Fanqi Wan, Jiajian Guo, Xiaojun Quan, Qifan Wang

Comments Accepted by ICLR 2025(spotlight)

Grams: Gradient Descent with Adaptive Momentum Scaling

Yang Cao, Xiaoyu Li, Zhao Song

Comments SCOPE Workshop @ ICLR 2025

Number Cookbook: Number Understanding of Language Models and How to Improve It

Haotong Yang, Yi Hu, Shijia Kang, Zhouchen Lin, Muhan Zhang

Comments ICLR 2025 poster

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

Bokun Wang, Yunwen Lei, Yiming Ying, Tianbao Yang

Comments To appear in ICLR 2025

DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

Yutong Wang, Jiali Zeng, Xuebo Liu, Derek F. Wong, Fandong Meng, Jie Zhou, Min Zhang

Comments Accepted as a conference paper at ICLR 2025

Journal ref Published as a conference paper at ICLR 2025

What to align in multimodal contrastive learning?

Benoit Dufumier, Javiera Castillo-Navarro, Devis Tuia, Jean-Philippe Thiran

Comments ICLR 2025, 25 pages

Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator

Xin Zhang, Jiawei Du, Ping Liu, Joey Tianyi Zhou

Comments Accepted to ICLR 2025

Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing

Peter Lippmann, Gerrit Gerhartz, Roman Remme, Fred A. Hamprecht

Comments To be published in proceedings of ICLR 2025

Statistical Advantages of Perturbing Cosine Router in Mixture of Experts

Huy Nguyen, Pedram Akbarian, Trang Pham, Trang Nguyen, Shujian Zhang, Nhat Ho

Comments Accepted to ICLR 2025

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, Dong Yu

Comments ICLR 2025

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

Boqian Wu, Qiao Xiao, Shunxin Wang, Nicola Strisciuglio, Mykola Pechenizkiy, Maurice van Keulen, Decebal Constantin Mocanu, Elena Mocanu

Comments Accepted at ICLR 2025

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups

Zakhar Shumaylov, Peter Zaika, James Rowbottom, Ferdia Sherry, Melanie Weber, Carola-Bibiane Schönlieb

Comments 44 pages; accepted at ICLR 2025

Transformer Block Coupling and its Correlation with Generalization in LLMs

Murdock Aubry, Haoming Meng, Anton Sugolov, Vardan Papyan

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR 2025)

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

Yuzhe Gu, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen

Comments Accepted by ICLR 2025. Code is available at https://github.com/open-compass/ANAH

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises

Zirun Guo, Tao Jin

Comments Accepted at ICLR 2025