ICLR

Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning

Qian Wang, Yuchen Gao, Zhenheng Tang, Bingqiao Luo, Nuo Chen, Bingsheng He

Comments Accepted at ICLR 2025 Financial AI Workshop

Fast Feedforward 3D Gaussian Splatting Compression

Yihang Chen, Qianyi Wu, Mengyao Li, Weiyao Lin, Mehrtash Harandi, Jianfei Cai

Comments Project Page: https://yihangchen-ee.github.io/project_fcgs/ Code: https://github.com/yihangchen-ee/fcgs/

Journal ref ICLR 2025

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Sreyan Ghosh, Sonal Kumar, Zhifeng Kong, Rafael Valle, Bryan Catanzaro, Dinesh Manocha

Comments Accepted at ICLR 2025. Code and Checkpoints available here: https://github.com/Sreyan88/Synthio

Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

Jiyeon Kim, Hyunji Lee, Hyowon Cho, Joel Jang, Hyeonbin Hwang, Seungpil Won, Youbin Ahn, Dohaeng Lee, Minjoon Seo

Comments ICLR 2025, Oral

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

Leqi Shen, Tianxiang Hao, Tao He, Sicheng Zhao, Yifeng Zhang, Pengzhang Liu, Yongjun Bao, Guiguang Ding

Comments ICLR 2025

Robustness Inspired Graph Backdoor Defense

Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang

Comments Accepted by ICLR 2025 (Oral)

FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee

Puheng Li, James Zou, Linjun Zhang

Comments Accepted at ICLR 2023

Towards Interpretable Protein Structure Prediction with Sparse Autoencoders

Nithin Parsan, David J. Yang, John J. Yang

Comments Published at the GEMBio ICLR 2025 Workshop

ReSi: A Comprehensive Benchmark for Representational Similarity Measures

Max Klabunde, Tassilo Wald, Tobias Schumacher, Klaus Maier-Hein, Markus Strohmaier, Florian Lemmerich

Comments ICLR 2025. Code and data at https://github.com/mklabunde/resi

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

Haoyu Wang, Sunhao Dai, Haiyuan Zhao, Liang Pang, Xiao Zhang, Gang Wang, Zhenhua Dong, Jun Xu, Ji-Rong Wen

Comments ICLR 2025

The Space Between: On Folding, Symmetries and Sampling

Michal Lewandowski, Bernhard Heinzl, Raphael Pisoni, Bernhard A. Moser

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

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

Tristan Tomilin, Meng Fang, Mykola Pechenizkiy

Comments Accepted to ICLR 2025

Exploring Bias in over 100 Text-to-Image Generative Models

Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian

Comments Accepted to ICLR 2025 Workshop on Open Science for Foundation Models (SCI-FM)

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

Qinghao Ye, Xianhan Zeng, Fu Li, Chunyuan Li, Haoqi Fan

Comments Accepted by ICLR 2025

Video Action Differencing

James Burgess, Xiaohan Wang, Yuhui Zhang, Anita Rau, Alejandro Lozano, Lisa Dunlap, Trevor Darrell, Serena Yeung-Levy

Comments ICLR 2025 (International Conference on Learning Representations) Project page: http://jmhb0.github.io/viddiff Benchmark: https://huggingface.co/datasets/jmhb/VidDiffBench

RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

Dhruv Gautam, Spandan Garg, Jinu Jang, Neel Sundaresan, Roshanak Zilouchian Moghaddam

Comments ICLR 2025 Camera Ready

Automated Benchmark Generation for Repository-Level Coding Tasks

Konstantinos Vergopoulos, Mark Niklas Müller, Martin Vechev

Comments Accepted at DL4C@ICLR'25 and FMWild@ICLR'25

TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation

Chenghan Li, Mingchen Li, Ruisheng Diao

Comments ICLR 2025

The Computational Complexity of Positive Non-Clashing Teaching in Graphs

Robert Ganian, Liana Khazaliya, Fionn Mc Inerney, Mathis Rocton

Comments The short version of this paper will appear in the proceedings of ICLR 2025

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

Martin Kuo, Jingyang Zhang, Jianyi Zhang, Minxue Tang, Louis DiValentin, Aolin Ding, Jingwei Sun, William Chen, Amin Hass, Tianlong Chen, Yiran Chen, Hai Li

Comments ICLR'25 Poster. Project page and code is available at https://ppa-iclr2025.my.canva.site/

Equivariant Masked Position Prediction for Efficient Molecular Representation

Junyi An, Chao Qu, Yun-Fei Shi, XinHao Liu, Qianwei Tang, Fenglei Cao, Yuan Qi

Comments 24 pages, 6 figures

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li

Comments International Conference on Learning Representations (ICLR), 2025

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

Yucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu

Comments Accepted at ICLR 2025

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise

Enea Monzio Compagnoni, Tianlin Liu, Rustem Islamov, Frank Norbert Proske, Antonio Orvieto, Aurelien Lucchi

Comments Accepted at ICLR 2025 (Poster); An earlier version, titled 'SDEs for Adaptive Methods: The Role of Noise' and dated May 2024, is available on OpenReview

Cut Your Losses in Large-Vocabulary Language Models

Erik Wijmans, Brody Huval, Alexander Hertzberg, Vladlen Koltun, Philipp Krähenbühl

Comments To appear in ICLR 2025 (Oral). Code is available at https://github.com/apple/ml-cross-entropy

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Zhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama, Jiasen Lu, Yoon Kim

Comments ICLR 2025

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions

Nate Gillman, Daksh Aggarwal, Michael Freeman, Saurabh Singh, Chen Sun

Comments Camera ready version (ICLR 2025). Code at https://nategillman.com/fourier-head

Transformers Provably Solve Parity Efficiently with Chain of Thought

Juno Kim, Taiji Suzuki

Comments ICLR 2025 Oral

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

Onkar Susladkar, Jishu Sen Gupta, Chirag Sehgal, Sparsh Mittal, Rekha Singhal

Comments Accepted in ICLR 2025 (spotlight paper)

Chemistry-Inspired Diffusion with Non-Differentiable Guidance

Yuchen Shen, Chenhao Zhang, Sijie Fu, Chenghui Zhou, Newell Washburn, Barnabás Póczos

Comments accepted by ICLR 2025