ICLR

To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation

Kaustubh D. Dhole

Comments 1st workshop of "Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI" at ICLR 2025

Neural Interactive Proofs

Lewis Hammond, Sam Adam-Day

Comments ICLR'25 camera-ready version; 51 pages, 17 figures

PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations

Namgyu Kang, Jaemin Oh, Youngjoon Hong, Eunbyung Park

Comments Accepted by ICLR 2025. Project page: https://namgyukang.github.io/Physics-Informed-Gaussians/

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Riccardo Grazzi, Julien Siems, Arber Zela, Jörg K. H. Franke, Frank Hutter, Massimiliano Pontil

Comments V2: Correction to Theorem 1 and 2 and to point 3 of Proposition 1. V3: ICLR Camera Ready, V4: ICLR Camera Ready, added figures to theory section, updated modular arithmetic with brackets results because previous results did not contain multiplication

An Effective Theory of Bias Amplification

Arjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis Dohmatob

Comments Accepted to ICLR 2025

Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions

Michael J. Q. Zhang, W. Bradley Knox, Eunsol Choi

Comments Presented at ICLR 2025

Counterfactual Generative Modeling with Variational Causal Inference

Yulun Wu, Louie McConnell, Claudia Iriondo

Comments Published as a conference paper at ICLR 2025

Towards Neural Scaling Laws for Time Series Foundation Models

Qingren Yao, Chao-Han Huck Yang, Renhe Jiang, Yuxuan Liang, Ming Jin, Shirui Pan

Comments Accepted by the 13th International Conference on Learning Representations (ICLR 2025)

3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

Qizhi Pei, Rui Yan, Kaiyuan Gao, Jinhua Zhu, Lijun Wu

Comments Accepted by ICLR 2025

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

Yumeng Li, William Beluch, Margret Keuper, Dan Zhang, Anna Khoreva

Comments Accepted at ICLR 2025. Code: https://github.com/boschresearch/VSTAR and project page: https://yumengli007.github.io/VSTAR

Bridging Neural and Symbolic Representations with Transitional Dictionary Learning

Junyan Cheng, Peter Chin

Comments ICLR 2024

ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction

Tong Zhou, Shijin Duan, Gaowen Liu, Charles Fleming, Ramana Rao Kompella, Shaolei Ren, Xiaolin Xu

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

Towards Learning High-Precision Least Squares Algorithms with Sequence Models

Jerry Liu, Jessica Grogan, Owen Dugan, Ashish Rao, Simran Arora, Atri Rudra, Christopher Ré

Comments 75 pages, 18 figures. ICLR 2025

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, François Savard, Ahmed Masry, Shravan Nayak, Rabiul Awal, Mahsa Massoud, Amirhossein Abaskohi, Zichao Li, Suyuchen Wang, Pierre-André Noël, Mats Leon Richter, Saverio Vadacchino, Shubham Agarwal, Sanket Biswas, Sara Shanian, Ying Zhang, Noah Bolger, Kurt MacDonald, Simon Fauvel, Sathwik Tejaswi, Srinivas Sunkara, Joao Monteiro, Krishnamurthy DJ Dvijotham, Torsten Scholak, Nicolas Chapados, Sepideh Kharagani, Sean Hughes, M. Özsu, Siva Reddy, Marco Pedersoli, Yoshua Bengio, Christopher Pal, Issam Laradji, Spandana Gella, Perouz Taslakian, David Vazquez, Sai Rajeswar

Comments The project is hosted at https://bigdocs.github.io

Journal ref ICLR 2025 https://openreview.net/forum?id=UTgNFcpk0j

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu

Comments ICLR 2025 Oral

An Information Criterion for Controlled Disentanglement of Multimodal Data

Chenyu Wang, Sharut Gupta, Xinyi Zhang, Sana Tonekaboni, Stefanie Jegelka, Tommi Jaakkola, Caroline Uhler

Comments ICLR 2025

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

Chenyu Wang, Masatoshi Uehara, Yichun He, Amy Wang, Tommaso Biancalani, Avantika Lal, Tommi Jaakkola, Sergey Levine, Hanchen Wang, Aviv Regev

Comments ICLR 2025

Real-time design of architectural structures with differentiable mechanics and neural networks

Rafael Pastrana, Eder Medina, Isabel M. de Oliveira, Sigrid Adriaenssens, Ryan P. Adams

Comments International Conference on Learning Representations (ICLR) 2025

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kajić, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Pinelopi Papalampidi, Ira Ktena, Chris Knutsen, Cyrus Rashtchian, Anant Nawalgaria, Jordi Pont-Tuset, Aida Nematzadeh

Comments Accepted to ICLR 2025 (Spotlight)

Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs

Wei Hung, Shao-Hua Sun, Ping-Chun Hsieh

Comments 23 pages, 14 figures. Accepted at ICLR 2025

RaSA: Rank-Sharing Low-Rank Adaptation

Zhiwei He, Zhaopeng Tu, Xing Wang, Xingyu Chen, Zhijie Wang, Jiahao Xu, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang

Comments ICLR 2025

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition

Jiahang Cao, Qiang Zhang, Hanzhong Guo, Jiaxu Wang, Hao Cheng, Renjing Xu

Comments Accepted to ICLR 2025 Generative Models for Robot Learning Workshop

Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene

Jiahao Wu, Rui Peng, Zhiyan Wang, Lu Xiao, Luyang Tang, Jinbo Yan, Kaiqiang Xiong, Ronggang Wang

Comments ICLR 2025

Counterfactual Realizability

Arvind Raghavan, Elias Bareinboim

Comments published at ICLR'25 (spotlight)

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking

Yijie Xu, Aiwei Liu, Xuming Hu, Lijie Wen, Hui Xiong

Comments Accepted by the ICLR 2025 Workshop on GenAI Watermarking

Cauchy-Schwarz Regularizers

Sueda Taner, Ziyi Wang, Christoph Studer

Comments Accepted to ICLR 2025

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

Haowen Pan, Xiaozhi Wang, Yixin Cao, Zenglin Shi, Xun Yang, Juanzi Li, Meng Wang

Comments ICLR 2025

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki

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

Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

Yuhan Chen, Yihong Luo, Yifan Song, Pengwen Dai, Jing Tang, Xiaochun Cao

Comments The first two authors contributed equally to this work; ICLR 2025

PICASO: Permutation-Invariant Context Composition with State Space Models

Tian Yu Liu, Alessandro Achille, Matthew Trager, Aditya Golatkar, Luca Zancato, Stefano Soatto

Comments Published in The Thirteenth International Conference on Learning Representations, ICLR 2025