ICLR

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

Ling Yang, Zhaochen Yu, Tianjun Zhang, Minkai Xu, Joseph E. Gonzalez, Bin Cui, Shuicheng Yan

Comments ICLR 2025. Project: https://github.com/YangLing0818/SuperCorrect-llm

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen

Comments ICLR 2025 Oral;GitHub:https://github.com/quchangle1/DRAFT

Adaptive Batch Size for Privately Finding Second-Order Stationary Points

Daogao Liu, Kunal Talwar

Comments Accepted to ICLR 2025. This version corrects an error by introducing a new subprocedure for escaping saddle points and also addresses minor typos

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, Lilian Weng, Aleksander Mądry

Comments 10 pages, 17 pages appendix. Equal contribution by first seven authors, authors randomized. ICLR version

Efficient Inference for Large Language Model-based Generative Recommendation

Xinyu Lin, Chaoqun Yang, Wenjie Wang, Yongqi Li, Cunxiao Du, Fuli Feng, See-Kiong Ng, Tat-Seng Chua

Comments Accepted by ICLR 2025

Better Instruction-Following Through Minimum Bayes Risk

Ian Wu, Patrick Fernandes, Amanda Bertsch, Seungone Kim, Sina Pakazad, Graham Neubig

Comments Accepted to ICLR 2025 (Spotlight); Camera Ready

Attention layers provably solve single-location regression

Pierre Marion, Raphaël Berthier, Gérard Biau, Claire Boyer

Comments 42 pages, 10 figures. Accepted to ICLR 2025

Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

Minghan Chen, Guikun Chen, Wenguan Wang, Yi Yang

Comments ICLR 2025; project page: https://github.com/Dreamer312/Hydra-SGG

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang

Comments Accepted by The Thirteenth International Conference on Learning Representations (ICLR 2025). Code is available at https://github.com/AuroraZengfh/Local-Prompt

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

Learning Harmonized Representations for Speculative Sampling

Lefan Zhang, Xiaodan Wang, Yanhua Huang, Ruiwen Xu

Comments Published as a conference paper at ICLR 2025

Training-Free Activation Sparsity in Large Language Models

James Liu, Pragaash Ponnusamy, Tianle Cai, Han Guo, Yoon Kim, Ben Athiwaratkun

Comments Rev. 2: ICLR 2025 Acceptance (Spotlight)

Towards Semantic Equivalence of Tokenization in Multimodal LLM

Shengqiong Wu, Hao Fei, Xiangtai Li, Jiayi Ji, Hanwang Zhang, Tat-Seng Chua, Shuicheng Yan

Comments ICLR-2025. The project page: https://chocowu.github.io/SeTok-web/

MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures

Anvith Thudi, Chris J. Maddison

Comments Proceedings of the 13th International Conference on Learning Representations

Can LLMs Solve longer Math Word Problems Better?

Xin Xu, Tong Xiao, Zitong Chao, Zhenya Huang, Can Yang, Yang Wang

Comments Accepted to ICLR 2025

Journal ref International Conference on Learning Representations (ICLR 2025)

Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints

Mihaela Cătălina Stoian, Eleonora Giunchiglia

Comments Accepted at ICLR 2025

Multi-Perspective Data Augmentation for Few-shot Object Detection

Anh-Khoa Nguyen Vu, Quoc-Truong Truong, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Tam V. Nguyen

Comments ICLR 2025

SBSC: Step-By-Step Coding for Improving Mathematical Olympiad Performance

Kunal Singh, Ankan Biswas, Sayandeep Bhowmick, Pradeep Moturi, Siva Kishore Gollapalli

Comments Published as a full conference paper at ICLR 2025. Shorter(Early) Version accepted at NeurIPS'24 MATH-AI track

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

Runyi Hu, Jie Zhang, Yiming Li, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang

Comments International Conference on Learning Representations (ICLR) 2025

UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models

Xin Xu, Jiaxin Zhang, Tianhao Chen, Zitong Chao, Jishan Hu, Can Yang

Comments Accepted to ICLR 2025

Journal ref International Conference on Learning Representations (ICLR 2025)

Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

Yuda Song, Hanlin Zhang, Carson Eisenach, Sham Kakade, Dean Foster, Udaya Ghai

Comments ICLR 2025; 41 pages, 19 figures

Scattered Forest Search: Smarter Code Space Exploration with LLMs

Jonathan Light, Yue Wu, Yiyou Sun, Wenchao Yu, Yanchi liu, Xujiang Zhao, Ziniu Hu, Haifeng Chen, Wei Cheng

Comments Accepted at ICLR 2025 Conference

SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

Koichi Namekata, Sherwin Bahmani, Ziyi Wu, Yash Kant, Igor Gilitschenski, David B. Lindell

Comments ICLR 2025. Project page: https://kmcode1.github.io/Projects/SG-I2V/

Cross-Entropy Is All You Need To Invert the Data Generating Process

Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David Klindt

Comments ICLR 2025 (oral) camera ready

Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

Peiwen Sun, Sitong Cheng, Xiangtai Li, Zhen Ye, Huadai Liu, Honggang Zhang, Wei Xue, Yike Guo

Comments Accepted by ICLR 2025

Ward: Provable RAG Dataset Inference via LLM Watermarks

Nikola Jovanović, Robin Staab, Maximilian Baader, Martin Vechev

Comments ICLR 2025

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

Yu Chen, Jiatai Huang, Yan Dai, Longbo Huang

Comments Accepted by the Thirteenth International Conference on Learning Representations

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Shengpeng Ji, Ziyue Jiang, Wen Wang, Yifu Chen, Minghui Fang, Jialong Zuo, Qian Yang, Xize Cheng, Zehan Wang, Ruiqi Li, Ziang Zhang, Xiaoda Yang, Rongjie Huang, Yidi Jiang, Qian Chen, Siqi Zheng, Zhou Zhao

Comments Accepted by ICLR 2025

SONICS: Synthetic Or Not -- Identifying Counterfeit Songs

Md Awsafur Rahman, Zaber Ibn Abdul Hakim, Najibul Haque Sarker, Bishmoy Paul, Shaikh Anowarul Fattah

Comments Accepted to ICLR 2025. Project url: https://github.com/awsaf49/sonics

GOAL: A Generalist Combinatorial Optimization Agent Learner

Darko Drakulic, Sofia Michel, Jean-Marc Andreoli

Comments Accepted to ICLR 2025

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

Qijun Gan, Song Wang, Shengtao Wu, Jianke Zhu

Comments ICLR 2025 Spotlight