ICML 2025 Workshop AI4MATH Submissions

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, Dacheng Tao
- Published: 09 Jul 2025, Last Modified: 16 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment
Jiyao Zhang, Chengli Zhong, Hui Xu, Li Qige, Jiajia Tian, Yi Zhou
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
IntegralBench: Benchmarking LLMs with Definite Integral Problems
Bintao Tang, Xin Yang, Yuhao Wang, Zixuan Qiu, Zimo Ji, Wenyuan Jiang
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Physics-Constrained Symbolic Regression from Imagery
Zhenyu Yu, MOHD YAMANI IDNA IDRIS, Pei Wang
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Temporal Sampling for Forgotten Reasoning in LLMs
Yuetai Li, Zhangchen Xu, Fengqing Jiang, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Xiang Yue, Radha Poovendran
- Published: 09 Jul 2025, Last Modified: 30 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Graph Neural Networks for Tensor Product Decompositions of Lie Algebra Representations
Max Vargas, Helen Jenne, Davis Brown, Henry Kvinge
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
Wenlong Deng, Yi Ren, Muchen Li, Danica J. Sutherland, Xiaoxiao Li, Christos Thrampoulidis
- Published: 09 Jul 2025, Last Modified: 16 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Token Hidden Reward: Steering Exploration-Exploitation in GRPO Training
Wenlong Deng, Yi Ren, Danica J. Sutherland, Christos Thrampoulidis, Xiaoxiao Li
- Published: 09 Jul 2025, Last Modified: 16 Jul 2025
- AI4Math@ICML25 Oral
- Readers: Everyone
Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
Kazuki Yoda, Kazuhiko Kawamoto, Hiroshi Kera
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
Zihao Zeng, Xuyao Huang, Boxiu Li, Hao Zhang, Zhijie Deng
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Plane Geometry Diagram Formalization via Vision-Language Models
Xiaoteng Cui, Yi Liu
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Solving Inequality Proofs with Large Language Models
Jiayi Sheng, Luna Lyu, Jikai Jin, Tony Xia, Alex Gu, James Zou, Pan Lu
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
COAST: Intelligent Time-Adaptive Neural Operators
Zhikai Wu, Shiyang Zhang, Sizhuang He, Sifan Wang, Min Zhu, Anran Jiao, Lu Lu, David van Dijk
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Lean Meets Theoretical Computer Science: Scalable Synthesis of Theorem Proving Challenges in Formal-Informal Pairs
Terry Jingchen Zhang, Wenyuan Jiang, Rongchuan Liu, Yisong Wang, Ning Wang, Junran Yang, Yinya Huang, Mrinmaya Sachan
- Published: 09 Jul 2025, Last Modified: 30 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Reward Inside the Model: A Lightweight Hidden‑State Reward Model for LLM's Best-of-N sampling
Jizhou Guo, Zhaomin Wu, Philip S. Yu
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Verina: Benchmarking Verifiable Code Generation
Zhe Ye, Zhengxu Yan, Jingxuan He, Timothe Kasriel, Kaiyu Yang, Dawn Song
- Published: 09 Jul 2025, Last Modified: 16 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Governing Equation Discovery from Data Based on Differential Invariants
Lexiang Hu, Yikang Li, Zhouchen Lin
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Vision Language Models are Biased: Counting legs of an animal is surprisingly hard
An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, Daeyoung Kim
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
The Challenge of Teaching Reasoning to LLMs Without RL or Distillation
Wei Du, Branislav Kisacanin, George Armstrong, Shubham Toshniwal, Ivan Moshkov, Alexan Ayrapetyan, Sadegh Mahdavi, Dan Zhao, Shizhe Diao, Dragan Mašulović, Advaith Avadhanam, Max Wang, Shitij Govil, Sri Yanamandra, Mihir Tandon, Sriram Ananthakrishnan, Vedant Rathi, David Zhang, Joonseok Kang, Leon Luo et al. (4 additional authors not shown)
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev, Maria Drencheva, Kristian Minchev, Mislav Balunovic, Nikola Jovanović, Martin Vechev
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
Matěj Kripner, Michal Sustr, Milan Straka
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
POD-KAN-NO: a physically interpretable neural operator
Yanyu Ke
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
Amrith Setlur, Matthew Y. R. Yang, Charlie Victor Snell, Jeremiah Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
Understanding R1-Zero-Like Training: A Critical Perspective
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin
- Published: 09 Jul 2025, Last Modified: 25 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone
The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
Xinyu Zhu, Mengzhou Xia, Zhepei Wei, Wei-Lin Chen, Danqi Chen, Yu Meng
- Published: 09 Jul 2025, Last Modified: 26 Jul 2025
- AI4Math@ICML25 Poster
- Readers: Everyone