ICLR

Glauber Generative Model: Discrete Diffusion Models via Binary Classification

Harshit Varma, Dheeraj Nagaraj, Karthikeyan Shanmugam

Comments ICLR 2025

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon, David Harel

Comments Published at ICLR 2025. (Link: https://openreview.net/forum?id=cJd1BgZ9CS)

Journal ref The 13th International Conference on Learning Representations (ICLR), 2025

Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery

Guankun Wang, Long Bai, Wan Jun Nah, Jie Wang, Zhaoxi Zhang, Zhen Chen, Jinlin Wu, Mobarakol Islam, Hongbin Liu, Hongliang Ren

Comments The manuscript is accepted by ICLR 2025 FM-Wild Workshop

CromSS: Cross-modal pre-training with noisy labels for remote sensing image segmentation

Chenying Liu, Conrad Albrecht, Yi Wang, Xiao Xiang Zhu

Comments The 1st short version was accepted as an oral presentation by ICLR 2024 ML4RS workshop. The 2nd extended version was accepted by IEEE TGRS

Efficient Learning With Sine-Activated Low-rank Matrices

Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey

Comments The first two authors contributed equally. Paper accepted at ICLR 2025

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

Xin Wang, Yu Zheng, Zhongwei Wan, Mi Zhang

Comments ICLR 2025; Code available at: AIoT-MLSys-Lab/SVD-LLM" target="_blank" rel="noopener">https://github.com/AIoT-MLSys-Lab/SVD-LLM

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Xuandong Zhao, Lei Li, Yu-Xiang Wang

Comments ICLR 2025

Learning under Temporal Label Noise

Sujay Nagaraj, Walter Gerych, Sana Tonekaboni, Anna Goldenberg, Berk Ustun, Thomas Hartvigsen

Comments The Thirteenth International Conference on Learning Representations (ICLR 2025)

A Coefficient Makes SVRG Effective

Yida Yin, Zhiqiu Xu, Zhiyuan Li, Trevor Darrell, Zhuang Liu

Comments Published in ICLR 2025

Distributed Black-box Attack: Do Not Overestimate Black-box Attacks

Han Wu, Sareh Rowlands, Johan Wahlstrom

Comments Accepted by ICLR Workshop, 2025

Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models

Jonas Thietke, Andreas Müller, Denis Lukovnikov, Asja Fischer, Erwin Quiring

Comments 8 pages, 3 figures, WMark@ICLR

Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation

He Zhang, Xinyi Fu, John M. Carroll

Comments This paper will appear at ICLR 2025 Workshop on Bidirectional Human-AI Alignment

DarkBench: Benchmarking Dark Patterns in Large Language Models

Esben Kran, Hieu Minh "Jord" Nguyen, Akash Kundu, Sami Jawhar, Jinsuk Park, Mateusz Maria Jurewicz

Comments Accepted as an Oral paper at ICLR 2025

Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

Songyuan Zhang, Oswin So, Mitchell Black, Chuchu Fan

Comments 31 pages, 15 figures; Accepted by the thirteenth International Conference on Learning Representations (ICLR 2025)

Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

Milad Khademi Nori, Il-Min Kim, Guanghui Wang

Comments Accepted ICLR 2025

RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks

Nazia Tasnim, Bryan A. Plummer

Comments Accepted as a conference paper in ICLR, 2025

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal

Comments ICLR 2025; The first two authors contributed equally; Project page: https://safree-safe-t2i-t2v.github.io/

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

Po-han Li, Sandeep P. Chinchali, Ufuk Topcu

Journal ref Published at ICLR 2025

Agents' Room: Narrative Generation through Multi-step Collaboration

Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, Mirella Lapata

Comments Published as a conference paper at ICLR 2025

DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image

Qingxuan Wu, Zhiyang Dou, Sirui Xu, Soshi Shimada, Chen Wang, Zhengming Yu, Yuan Liu, Cheng Lin, Zeyu Cao, Taku Komura, Vladislav Golyanik, Christian Theobalt, Wenping Wang, Lingjie Liu

Comments ICLR 2025

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Duy-Kien Nguyen, Mahmoud Assran, Unnat Jain, Martin R. Oswald, Cees G. M. Snoek, Xinlei Chen

Comments In Proceeding of ICLR'2025

Protein Discovery with Discrete Walk-Jump Sampling

Nathan C. Frey, Daniel Berenberg, Karina Zadorozhny, Joseph Kleinhenz, Julien Lafrance-Vanasse, Isidro Hotzel, Yan Wu, Stephen Ra, Richard Bonneau, Kyunghyun Cho, Andreas Loukas, Vladimir Gligorijevic, Saeed Saremi

Comments ICLR 2024 oral presentation, top 1.2% of submissions; {ICLR 2023 Physics for Machine Learning, NeurIPS 2023 GenBio, MLCB 2023} Spotlight

Journal ref The Twelfth International Conference on Learning Representations, 2024

Diverse Projection Ensembles for Distributional Reinforcement Learning

Moritz A. Zanger, Wendelin Böhmer, Matthijs T. J. Spaan

Comments ICLR 2024

Radar: Fast Long-Context Decoding for Any Transformer

Yongchang Hao, Mengyao Zhai, Hossein Hajimirsadeghi, Sepidehsadat Hosseini, Frederick Tung

Comments Accepted @ ICLR 2025

6D Object Pose Tracking in Internet Videos for Robotic Manipulation

Georgy Ponimatkin, Martin Cífka, Tomáš Souček, Médéric Fourmy, Yann Labbé, Vladimir Petrik, Josef Sivic

Comments Accepted to ICLR 2025. Project page available at https://ponimatkin.github.io/wildpose/

Probability-Flow ODE in Infinite-Dimensional Function Spaces

Kunwoo Na, Junghyun Lee, Se-Young Yun, Sungbin Lim

Comments 26 pages, 8 figures. Accepted to the ICLR 2025 DeLTa Workshop

MastermindEval: A Simple But Scalable Reasoning Benchmark

Jonas Golde, Patrick Haller, Fabio Barth, Alan Akbik

Comments 9 pages, 2 figures, 4 tables. In: ICLR 2025 Workshop on Reasoning and Planning for Large Language Models

Uni-Sign: Toward Unified Sign Language Understanding at Scale

Zecheng Li, Wengang Zhou, Weichao Zhao, Kepeng Wu, Hezhen Hu, Houqiang Li

Comments Accepted by ICLR 2025

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Yiming Wang, Pei Zhang, Baosong Yang, Derek F. Wong, Rui Wang

Comments Accepted by ICLR 2025

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan

Comments Accepted to ICLR 2025. Codes and Supplementary Material: https://github.com/viiika/Meissonic