ICLR

Towards Continuous Reuse of Graph Models via Holistic Memory Diversification

Ziyue Qiao, Junren Xiao, Qingqiang Sun, Meng Xiao, Xiao Luo, Hui Xiong

Comments Accepted by ICLR 2025

Lasso Bandit with Compatibility Condition on Optimal Arm

Harin Lee, Taehyun Hwang, Min-hwan Oh

Comments Published at ICLR 2025

A Second-Order Perspective on Model Compositionality and Incremental Learning

Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega, Monica Millunzi, Simone Calderara, Rita Cucchiara

Comments Accepted to ICLR 2025 (Spotlight)

Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

Rheeya Uppaal, Apratim Dey, Yiting He, Yiqiao Zhong, Junjie Hu

Comments Accepted to ICLR 2025

Contextualizing biological perturbation experiments through language

Menghua Wu, Russell Littman, Jacob Levine, Lin Qiu, Tommaso Biancalani, David Richmond, Jan-Christian Huetter

Comments The Thirteenth International Conference on Learning Representations (2025)

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

Jianhao Huang, Zixuan Wang, Jason D. Lee

Comments ICLR 2025 Spotlight

Variational Bayesian Pseudo-Coreset

Hyungi Lee, Seungyoo Lee, Juho Lee

Comments The Thirteenth International Conference on Learning Representations (ICLR2025)

Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?

Charles Dawson, Van Tran, Max Z. Li, Chuchu Fan

Comments Published at ICLR 2025

Reward Learning from Multiple Feedback Types

Yannick Metz, András Geiszl, Raphaël Baur, Mennatallah El-Assady

Comments Published as a conference paper at ICLR 2025

Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning

Giseung Park, Youngchul Sung

Comments Accepted to ICLR 2025

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Xunhao Lai, Jianqiao Lu, Yao Luo, Yiyuan Ma, Xun Zhou

Comments Accepted at ICLR 2025 (Oral)

Dimension Agnostic Neural Processes

Hyungi Lee, Chaeyun Jang, Dongbok Lee, Juho Lee

Comments 10 pages, 5 figures, Accepted to ICLR 2025 (International Conference on Learning Representations)

Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization

Yuanchao Wang, Zhao-Rong Lai, Tianqi Zhong

Comments ICLR 2025

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs

Xin Gao, Jian Pu

Comments 10 pages, 4 figures, ICLR 2025

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Makoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba

Comments To appear at the 13th International Conference on Learning Representations (ICLR 2025) as a Spotlight presentation

Scalable Decentralized Learning with Teleportation

Yuki Takezawa, Sebastian U. Stich

Comments ICLR 2025

Logical Consistency of Large Language Models in Fact-checking

Bishwamittra Ghosh, Sarah Hasan, Naheed Anjum Arafat, Arijit Khan

Comments Published at ICLR 2025

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Fan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang

Comments The first three authors contributed equally to this work; Accepted by ICLR 2025

TRENDy: Temporal Regression of Effective Nonlinear Dynamics

Matthew Ricci, Guy Pelc, Zoe Piran, Noa Moriel, Mor Nitzan

Comments 10 pages, 14 appendix pages, 5 figures, 7 appendix figures. Updated to reflect acceptance at ICLR 2025. Minor formatting updates

I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength

Wanquan Feng, Jiawei Liu, Pengqi Tu, Tianhao Qi, Mingzhen Sun, Tianxiang Ma, Songtao Zhao, Siyu Zhou, Qian He

Comments Accepted to ICLR 2025, Project page: https://wanquanf.github.io/I2VControlCamera

DELTA: Dense Efficient Long-range 3D Tracking for any video

Tuan Duc Ngo, Peiye Zhuang, Chuang Gan, Evangelos Kalogerakis, Sergey Tulyakov, Hsin-Ying Lee, Chaoyang Wang

Comments ICLR 2025. Project Page: https://snap-research.github.io/DELTA/

FACTS: A Factored State-Space Framework For World Modelling

Li Nanbo, Firas Laakom, Yucheng Xu, Wenyi Wang, Jürgen Schmidhuber

Comments Code released in https://github.com/NanboLi/FACTS

Journal ref ICLR 2025

Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA

Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster

Comments ICLR 2025; 49 pages, 17 figures, 19 tables

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

Zhangheng Li, Keen You, Haotian Zhang, Di Feng, Harsh Agrawal, Xiujun Li, Mohana Prasad Sathya Moorthy, Jeff Nichols, Yinfei Yang, Zhe Gan

Comments Accepted to ICLR 2025

A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics

Katharina Friedl, Noémie Jaquier, Jens Lundell, Tamim Asfour, Danica Kragic

Comments 28 pages, 16 figures. Accepted for publication in ICLR'25

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jimenez, Francois Fleuret, Pascal Frossard

Comments The first two authors contributed equally to this work. Accepted at ICLR 2025. Project website: https://lines-merging.github.io

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models

Shicheng Xu, Liang Pang, Yunchang Zhu, Huawei Shen, Xueqi Cheng

Comments ICLR 2025

ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

Yein Park, Chanwoong Yoon, Jungwoo Park, Donghyeon Lee, Minbyul Jeong, Jaewoo Kang

Comments ICLR 2025, 40 pages, 17 figures

GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

Dingyi Zhuang, Chonghe Jiang, Yunhan Zheng, Shenhao Wang, Jinhua Zhao

Comments ICLR 2025 Spotlight

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

Jiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

Comments Accepted as ICLR 2025 conference paper (26 pages, 16 tables, 9 figures)