ICLR

Neural Dueling Bandits: Preference-Based Optimization with Human Feedback

Arun Verma, Zhongxiang Dai, Xiaoqiang Lin, Patrick Jaillet, Bryan Kian Hsiang Low

Comments Accepted at ICLR 2025. Also, accepted at ICML 2024 Workshop on Foundations of Reinforcement Learning and Control

Proxy Denoising for Source-Free Domain Adaptation

Song Tang, Wenxin Su, Yan Gan, Mao Ye, Jianwei Zhang, Xiatian Zhu

Comments This paper is accepted by ICLR 2025 (Oral, Top 1.8%)

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

Simon Schrodi, David T. Hoffmann, Max Argus, Volker Fischer, Thomas Brox

Comments ICLR 2025 (Oral)

Discrete Distribution Networks

Lei Yang

Comments Published as a conference paper at ICLR 2025

EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos

Jilan Xu, Yifei Huang, Baoqi Pei, Junlin Hou, Qingqiu Li, Guo Chen, Yuejie Zhang, Rui Feng, Weidi Xie

Comments ICLR 2025

Possibility for Proactive Anomaly Detection

Jinsung Jeon, Jaehyeon Park, Sewon Park, Jeongwhan Choi, Minjung Kim, Noseong Park

Comments Accepted at ICLR 2025 I Can't Believe It's Not Better: Challenges in Applied Deep Learning Workshop (ICBINB)

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

Hongxin Zhang, Zeyuan Wang, Qiushi Lyu, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Behzad Dariush, Kwonjoon Lee, Yilun Du, Chuang Gan

Comments Published at ICLR 2025. 24 pages. The first three authors contributed equally

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

Ziqi Pang, Xin Xu, Yu-Xiong Wang

Comments ICLR 2025

Journal ref ICLR 2025

Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models

Andrea Tirinzoni, Ahmed Touati, Jesse Farebrother, Mateusz Guzek, Anssi Kanervisto, Yingchen Xu, Alessandro Lazaric, Matteo Pirotta

Comments Published at ICLR 2025

Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation

Samuel Maddock, Shripad Gade, Graham Cormode, Will Bullock

Comments Accepted to the Synthetic Data x Data Access Problem (SynthData) workshop @ ICLR 2025

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

Rui Dai, Sile Hu, Xu Shen, Yonggang Zhang, Xinmei Tian, Jieping Ye

Comments Accepted by ICLR 2025

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti, Alice Oh, Meeyoung Cha

Comments Accepted to ICLR 2025 Workshop - BiAlign (Bidirectional Human-AI Alignment)

Deep Audio Watermarks are Shallow: Limitations of Post-Hoc Watermarking Techniques for Speech

Patrick O'Reilly, Zeyu Jin, Jiaqi Su, Bryan Pardo

Comments ICLR 2025 Workshop on GenAI Watermarking

F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos

Zhaoyu Liu, Kan Jiang, Murong Ma, Zhe Hou, Yun Lin, Jin Song Dong

Comments ICLR 2025; Website URL: https://lzyandy.github.io/f3set-website/

AutoML Benchmark with shorter time constraints and early stopping

Israel Campero Jurado, Pieter Gijsbers, Joaquin Vanschoren

Comments Workshop on the Future of Machine Learning Data Practices and Repositories, ICLR 2025

Causal Graphical Models for Vision-Language Compositional Understanding

Fiorenzo Parascandolo, Nicholas Moratelli, Enver Sangineto, Lorenzo Baraldi, Rita Cucchiara

Comments Accepted at ICLR 2025

Second-Order Min-Max Optimization with Lazy Hessians

Lesi Chen, Chengchang Liu, Jingzhao Zhang

Comments ICLR 2025

TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights

Aiwei Liu, Haoping Bai, Zhiyun Lu, Yanchao Sun, Xiang Kong, Simon Wang, Jiulong Shan, Albin Madappally Jose, Xiaojiang Liu, Lijie Wen, Philip S. Yu, Meng Cao

Comments Published in ICLR 2025, code in https://github.com/exlaw/TIS-DPO

System-1.x: Learning to Balance Fast and Slow Planning with Language Models

Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal

Comments ICLR 2025 (Camera-Ready)

Unsupervised Model Tree Heritage Recovery

Eliahu Horwitz, Asaf Shul, Yedid Hoshen

Comments ICLR 2025. Project page: https://horwitz.ai/mother

Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction

M. Eren Akbiyik, Nedko Savov, Danda Pani Paudel, Nikola Popovic, Christian Vater, Otmar Hilliges, Luc Van Gool, Xi Wang

Comments Accepted to 13th International Conference on Learning Representations (ICLR 2025), 29 pages

A Model Zoo of Vision Transformers

Damian Falk, Léo Meynent, Florence Pfammatter, Konstantin Schürholt, Damian Borth

Comments Accepted at the ICLR Workshop on Neural Network Weights as a New Data Modality 2025

The Impact of Model Zoo Size and Composition on Weight Space Learning

Damian Falk, Konstantin Schürholt, Damian Borth

Comments Accepted at the ICLR Workshop on Neural Network Weights as a New Data Modality 2025

Using Reinforcement Learning to Integrate Subjective Wellbeing into Climate Adaptation Decision Making

Arthur Vandervoort, Miguel Costa, Morten W. Petersen, Martin Drews, Sonja Haustein, Karyn Morrissey, Francisco C. Pereira

Comments Accepted for presentation at Tackling Climate Change with Machine Learning workshop at ICLR 2025

Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation

Chenbin Zhang, Zhiqiang Hu, Chuchu Jiang, Wen Chen, Jie Xu, Shaoting Zhang

Comments ICLR 2025 Oral

Hierarchical protein backbone generation with latent and structure diffusion

Jason Yim, Marouane Jaakik, Ge Liu, Jacob Gershon, Karsten Kreis, David Baker, Regina Barzilay, Tommi Jaakkola

Comments ICLR 2025 Generative and Experimental Perspectives for Biomolecular Design Workshop

Text To 3D Object Generation For Scalable Room Assembly

Sonia Laguna, Alberto Garcia-Garcia, Marie-Julie Rakotosaona, Stylianos Moschoglou, Leonhard Helminger, Sergio Orts-Escolano

Comments Published at the ICLR 2025 Workshop on Synthetic Data

Beyond Glucose-Only Assessment: Advancing Nocturnal Hypoglycemia Prediction in Children with Type 1 Diabetes

Marco Voegeli, Sonia Laguna, Heike Leutheuser, Marc Pfister, Marie-Anne Burckhardt, Julia E Vogt

Comments Published at ICLR 2025 Workshop on AI for Children

Query-based Knowledge Transfer for Heterogeneous Learning Environments

Norah Alballa, Wenxuan Zhang, Ziquan Liu, Ahmed M. Abdelmoniem, Mohamed Elhoseiny, Marco Canini

Comments Accepted at ICLR'25

MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data

Wentao Li, Yizhe Chen, Jiangjie Qiu, Xiaonan Wang

Comments AI4MAT-ICLR-2025: ICLR 2025 Workshop on AI for Accelerated Materials Design