ICLR

DEPT: Decoupled Embeddings for Pre-training Language Models

Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, William F. Shen, Xinchi Qiu, Dongqi Cai, Yan Gao, Nicholas D. Lane

Comments Published as a conference paper at ICLR 2025

DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery

Yuanpei Liu, Kai Han

Comments Accepted as a conference paper at ICLR 2025

On the Spatial Structure of Mixture-of-Experts in Transformers

Daniel Bershatsky, Ivan Oseledets

Comments Accepted to ICLR 2025 Workshop on Sparsity in LLMs (SLLM)

PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networks

Youn-Yeol Yu, Jeongwhan Choi, Jaehyeon Park, Kookjin Lee, Noseong Park

Comments Accepted to ICLR 2025. Youn-Yeol Yu and Jeongwhan Choi contributed equally to this work

Language Models Are Implicitly Continuous

Samuele Marro, Davide Evangelista, X. Angelo Huang, Emanuele La Malfa, Michele Lombardi, Michael Wooldridge

Comments Published at ICLR 2025

Improving World Models using Deep Supervision with Linear Probes

Andrii Zahorodnii

Comments ICLR 2025 Workshop on World Models

Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs

Yu-Zhe Shi, Mingchen Liu, Fanxu Meng, Qiao Xu, Zhangqian Bi, Kun He, Lecheng Ruan, Qining Wang

Comments In International Conference on Learning Representations (ICLR'25)

Watermarking for AI Content Detection: A Review on Text, Visual, and Audio Modalities

Lele Cao

Comments Accepted by ICLR 2025 workshop on GenAI Watermarking

A Benchmark for Scalable Oversight Protocols

Abhimanyu Pallavi Sudhir, Jackson Kaunismaa, Arjun Panickssery

Comments Accepted at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Yucheng Suo, Fan Ma, Kaixin Shen, Linchao Zhu, Yi Yang

Comments ICLR 2025

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations

Yanshu Li

Comments Accepted by ICLR 2025 Workshop on Reasoning and Planning for LLMs, 25 pages, 13 tables

Noisy Test-Time Adaptation in Vision-Language Models

Chentao Cao, Zhun Zhong, Zhanke Zhou, Tongliang Liu, Yang Liu, Kun Zhang, Bo Han

Comments ICLR 2025

MetaSC: Test-Time Safety Specification Optimization for Language Models

Víctor Gallego

Comments Published at ICLR 2025 Workshop on Foundation Models in the Wild

Journal ref ICLR 2025 Workshop on Foundation Models in the Wild

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

Lehan Wang, Haonan Wang, Honglong Yang, Jiaji Mao, Zehong Yang, Jun Shen, Xiaomeng Li

Comments Accepted in ICLR 2025

Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

Junwei Zhou, Xueting Li, Lu Qi, Ming-Hsuan Yang

Comments 21 pages,17 figures. ICLR 2025 poster

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Sijun Tan, Siyuan Zhuang, Kyle Montgomery, William Y. Tang, Alejandro Cuadron, Chenguang Wang, Raluca Ada Popa, Ion Stoica

Comments Published as a conference paper at ICLR 2025

Differential Transformer

Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, Furu Wei

Comments Accepted as an Oral Presentation at ICLR 2025

CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention

Gaojie Lin, Jianwen Jiang, Chao Liang, Tianyun Zhong, Jiaqi Yang, Yanbo Zheng

Comments ICLR 2025 (Oral), Homepage: https://cyberhost.github.io/

Safety Layers in Aligned Large Language Models: The Key to LLM Security

Shen Li, Liuyi Yao, Lan Zhang, Yaliang Li

Comments Accepted by ICLR 2025. The code is available at https://github.com/listen0425/Safety-Layers

Preserving Diversity in Supervised Fine-Tuning of Large Language Models

Ziniu Li, Congliang Chen, Tian Xu, Zeyu Qin, Jiancong Xiao, Zhi-Quan Luo, Ruoyu Sun

Comments accepted by ICLR 2025

Learning Spatial-Semantic Features for Robust Video Object Segmentation

Xin Li, Deshui Miao, Zhenyu He, Yaowei Wang, Huchuan Lu, Ming-Hsuan Yang

Comments Published as a conference paper in ICLR 2025

Journal ref Proceedings of the 13th International Conference on Learning Representations (ICLR 2025)

Towards Domain Adaptive Neural Contextual Bandits

Ziyan Wang, Xiaoming Huo, Hao Wang

Comments Accepted at ICLR 2025

Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, Huajun Chen

Comments ICLR 2025 Camera-ready Version. Fix a caption typo in the current version

How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models

Pascal Chang, Jingwei Tang, Markus Gross, Vinicius C. Azevedo

Comments Accepted at ICLR 2024 (Oral)

Global-Order GFlowNets

Lluís Pastor-Pérez, Javier Alonso-Garcia, Lukas Mauch

Comments 8 pages, ICLR 2025 Workshop format

Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks

Mario Lino, Tobias Pfaff, Nils Thuerey

Comments 31 pages, 19 figures, Published as a conference paper at ICLR 2025

Journal ref The Thirteenth International Conference on Learning Representations, April 2025

Bootstrapped Model Predictive Control

Yuhang Wang, Hanwei Guo, Sizhe Wang, Long Qian, Xuguang Lan

Comments Published as a conference paper at ICLR 2025

Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

Junjie Chen, Xiangheng He, Yusuke Miyao, Danushka Bollegala

Comments Accepted to ICLR 2025 (spotlight)

How Feature Learning Can Improve Neural Scaling Laws

Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan

Comments Accepted as spotlight ICLR 2025

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Jianwen Jiang, Chao Liang, Jiaqi Yang, Gaojie Lin, Tianyun Zhong, Yanbo Zheng

Comments ICLR 2025 (Oral), Homepage: https://loopyavatar.github.io/