ICLR

Uncovering Latent Chain of Thought Vectors in Language Models

Jason Zhang, Scott Viteri

Comments This work was presented at the Workshop on Neural Network Weights as a New Data Modality at ICLR 2025

Morphing Tokens Draw Strong Masked Image Models

Taekyung Kim, Byeongho Heo, Dongyoon Han

Comments 24 pages, 16 tables, 8 figures. To be presented at ICLR'25

Narrowing Class-Wise Robustness Gaps in Adversarial Training

Fatemeh Amerehi, Patrick Healy

Comments 4 figures, ICLR 2025 Workshop on Foundation Models in the Wild

Towards Lighter and Robust Evaluation for Retrieval Augmented Generation

Alex-Razvan Ispas, Charles-Elie Simon, Fabien Caspani, Vincent Guigue

Comments 17 pages, 5 figures, published at 1st workshop of Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI at ICLR 25

Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

Comments Accepted at ICLR 2025 Workshop Deep Learning for Code

Rationalization Models for Text-to-SQL

Gaetano Rossiello, Nhan Pham, Michael Glass, Junkyu Lee, Dharmashankar Subramanian

Comments Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

Tao Zhang, Jinyong Wen, Zhen Chen, Kun Ding, Shiming Xiang, Chunhong Pan

Comments ICLR 2025. 27 pages, 13 figures, 21 tables

Differentially Private Steering for Large Language Model Alignment

Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal

Comments ICLR 2025 Camera Ready; Code: https://github.com/UKPLab/iclr2025-psa

Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images

Sichen Zhu, Yuchen Zhu, Molei Tao, Peng Qiu

Comments Accepted to ICLR 2025

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

Zhijian Zhuo, Ya Wang, Yutao Zeng, Xiaoqing Li, Xun Zhou, Jinwen Ma

Comments Accepted by ICLR 2025

NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

Wei-Bang Jiang, Yansen Wang, Bao-Liang Lu, Dongsheng Li

Comments The Thirteenth International Conference on Learning Representations

Journal ref The Thirteenth International Conference on Learning Representations, 2025

LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning

Zhuorui Ye, Stephanie Milani, Geoffrey J. Gordon, Fei Fang

Comments Accepted at ICLR 2025

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

Parshin Shojaee, Kazem Meidani, Shashank Gupta, Amir Barati Farimani, Chandan K Reddy

Comments ICLR 2025 Oral

Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors

Milad Sefidgaran, Abdellatif Zaidi, Piotr Krasnowski

Comments Accepted as a Spotlight Paper at ICLR 2025

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

Wenbo Hu, Jia-Chen Gu, Zi-Yi Dou, Mohsen Fayyaz, Pan Lu, Kai-Wei Chang, Nanyun Peng

Comments ICLR 2025

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

Yusu Qian, Hanrong Ye, Jean-Philippe Fauconnier, Peter Grasch, Yinfei Yang, Zhe Gan

Comments Accepted at ICLR 2025

Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

Han-Hung Lee, Yiming Zhang, Angel X. Chang

Comments ICLR 2025

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

Shoubin Yu, Jaehong Yoon, Mohit Bansal

Comments ICLR 2025; first two authors contributed equally. Project page: https://CREMA-VideoLLM.github.io/

Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems

Sejong Kim, Hyunseo Song, Hyunwoo Seo, Hyunjun Kim

Comments 15 pages, 3 figures, 11 tables. Accepted at ICLR 2025 Workshop on Advances in Financial AI. Code available at https://github.com/seohyunwoo-0407/GAR

ARC: Anchored Representation Clouds for High-Resolution INR Classification

Joost Luijmes, Alexander Gielisse, Roman Knyazhitskiy, Jan van Gemert

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

Object-Centric Pretraining via Target Encoder Bootstrapping

Nikola Đukić, Tim Lebailly, Tinne Tuytelaars

Comments ICLR 2025

Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMs

Benjamin Estermann, Roger Wattenhofer

Comments Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Yujin Potter, Zhun Wang, Zhuowen Yuan, Alexander Xiong, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Xuandong Zhao, Francesco Pinto, Zhen Xiang, Yu Gai, Zinan Lin, Dan Hendrycks, Bo Li, Dawn Song

Comments ICLR 2025

LipShiFT: A Certifiably Robust Shift-based Vision Transformer

Rohan Menon, Nicola Franco, Stephan Günnemann

Comments ICLR 2025 Workshop: VerifAI: AI Verification in the Wild

Journal ref ICLR 2025 Workshop: VerifAI: AI Verification in the Wild

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

Hejia Chen, Haoxian Zhang, Shoulong Zhang, Xiaoqiang Liu, Sisi Zhuang, Yuan Zhang, Pengfei Wan, Di Zhang, Shuai Li

Comments Accepted by ICLR'25

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection

Chuxin Wang, Wenfei Yang, Xiang Liu, Tianzhu Zhang

Comments Accepted by ICLR 2025. Project url: https://chuxwa.github.io/project_DEST/

Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation

Huan Ren, Wenfei Yang, Xiang Liu, Shifeng Zhang, Tianzhu Zhang

Comments Accepted by ICLR 2025. Project page is available at https://renhuan1999.github.io/SpherePose

ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning

Nilo Schwencke, Cyril Furtlehner

Comments accepted in ICLR 2025

Journal ref Proceedings of ICLR 2025

Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning

Mianchu Wang, Yue Jin, Giovanni Montana

Comments Published as a conference paper at ICLR 2025

Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources

Vibhhu Sharma, Bryan Wilder

Comments Accepted to ICLR 2025 as a Poster