Workshop
MATH-AI: The 3rd Workshop on Mathematical Reasoning and AI
Zhenwen Liang · Albert Q. Jiang · Katie Collins · Pan Lu · Kaiyu Yang · Sean Welleck · James McClelland
Room 217 - 219
Fri 15 Dec, 7 a.m. PST
Mathematical reasoning is a fundamental aspect of human cognition that has been studied by scholars ranging from philosophers to cognitive scientists and neuroscientists. Mathematical reasoning involves analyzing complex information, identifying patterns and relationships, and drawing logical conclusions from evidence. It is central to many applications in science, engineering, finance, and everyday contexts. Recent advancements in large language models (LLMs) have unlocked new opportunities at the intersection of artificial intelligence and mathematical reasoning, ranging from new methods that solve complex problems or prove theorems, to new forms of human-machine collaboration in mathematics and beyond. Our proposed workshop is centered on the intersection of deep learning and mathematical reasoning, with an emphasis on, but not limited to, large language models. Our guiding theme is: "To what extent can machine learning models comprehend mathematics, and what applications could arise from this capability?'' To address this question, we aim to bring together a diverse group of scholars from different backgrounds, institutions, and disciplines in our workshop. By hosting this workshop, we hope to stimulate insightful discussions that will guide future research and applications in this rapidly expanding field.
Schedule
Fri 7:00 a.m. - 7:30 a.m.
|
Invited Talk - AI4Crypto
(
Talk - Kristin Lauter
)
>
SlidesLive Video |
🔗 |
Fri 7:00 a.m. - 7:00 a.m.
|
Introduction and Opening Remarks
(
Opening Remarks
)
>
|
🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
Invited Talk - Exploring Mathematical Conjecturing – From Heuristic Search to Large Language Models
(
Talk - Moa Johansson
)
>
SlidesLive Video |
🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
Invited Talk - Axioms (and curiosity and attention) are all you need
(
Talk - Noah Goodman
)
>
SlidesLive Video |
🔗 |
Fri 8:30 a.m. - 9:00 a.m.
|
Coffee Break
|
🔗 |
Fri 9:00 a.m. - 10:00 a.m.
|
Panel Discussion
(
Panel
)
>
SlidesLive Video |
🔗 |
Fri 10:00 a.m. - 11:00 a.m.
|
Lunch Break
|
🔗 |
Fri 11:00 a.m. - 12:00 p.m.
|
Oral Paper Presentation
(
Oral Paper Presentation
)
>
|
🔗 |
Fri 11:00 a.m. - 11:15 a.m.
|
Learning the Greatest Divisor - Explainable Predictions in Transformers
(
Oral Paper Presentation by Francois Charton
)
>
SlidesLive Video |
🔗 |
Fri 11:15 a.m. - 11:30 a.m.
|
Lemur: Integrating Large Language Models in Automated Program Verification
(
Oral Paper Presentation by Nina Narodytska
)
>
SlidesLive Video |
🔗 |
Fri 11:30 a.m. - 11:45 a.m.
|
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
(
Oral Paper Presentation by Keiran Paster
)
>
SlidesLive Video |
🔗 |
Fri 11:45 a.m. - 12:00 p.m.
|
What Algorithms Can Transformers Learn? A Study in Length Generalization
(
Oral Paper Presentation by Hattie Zhou
)
>
SlidesLive Video |
🔗 |
Fri 12:00 p.m. - 12:30 p.m.
|
Invited Talk - AI can learn from data. But can it learn to reason?
(
Talk - Guy Van den Broeck
)
>
SlidesLive Video |
🔗 |
Fri 12:30 p.m. - 1:00 p.m.
|
Coffee Break
|
🔗 |
Fri 1:00 p.m. - 2:00 p.m.
|
Poster Session
(
Poster Session
)
>
|
🔗 |
Fri 2:00 p.m. - 2:30 p.m.
|
Invited Talk - Analogical Reasoning with Large Language Models
(
Talk - Xinyun Chen
)
>
SlidesLive Video |
🔗 |
Fri 2:30 p.m. - 3:00 p.m.
|
Invited Talk - Mechanisms of Symbol Processing for In-Context Learning in Transformers
(
Talk - Paul Smolensky
)
>
SlidesLive Video |
🔗 |
-
|
Navigating Beyond the Dead End: A Math Problem Solving Framework by Switching among Diverse Reasoning Thoughts ( Poster ) > link | Tengxiao Liu · Qipeng Guo · Yuqing Yang · Xiangkun Hu · Yue Zhang · Xipeng Qiu · Zheng Zhang 🔗 |
-
|
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search ( Poster ) > link |
19 presentersAbbas Mehrabian · Ankit Anand · Hyunjik Kim · Nicolas Sonnerat · Tudor Berariu · Matej Balog · Gheorghe Comanici · Andrew Lee · Anian Ruoss · Anna Bulanova · Daniel Toyama · Sam Blackwell · Bernardino Romera-Paredes · Laurent Orseau · Petar Veličković · Anurag Murty Naredla · Joonkyung Lee · Adam Wagner · Doina Precup |
-
|
Augmenting Large Language Models with Symbolic Rule Learning for Robust Numerical Reasoning ( Poster ) > link | Hadeel Al-Negheimish · Pranava Madhyastha · Alessandra Russo 🔗 |
-
|
Understanding Length Generalization by Thinking Like Transformers - Poster ( Poster ) > link | Hattie Zhou · Arwen Bradley · Etai Littwin · Noam Razin · Omid Saremi · Joshua Susskind · Samy Bengio · Preetum Nakkiran 🔗 |
-
|
Temperature-scaled large language models for Lean proofstep prediction ( Poster ) > link | Fabian Gloeckle · Baptiste Roziere · Amaury Hayat · Gabriel Synnaeve 🔗 |
-
|
Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures ( Poster ) > link | Michael Hersche · Francesco Di Stefano · Thomas Hofmann · Abu Sebastian · Abbas Rahimi 🔗 |
-
|
Reinforcement Learning in Control Theory: A New Approach to Mathematical Problem Solving ( Poster ) > link | Kala Bidi · Jean-Michel Coron · Amaury Hayat · Nathan Lichtlé 🔗 |
-
|
Can We Count on Deep Learning: Exploring and Characterizing Combinatorial Structures Using Machine Learning ( Poster ) > link | Helen Jenne · Herman Chau · Davis Brown · Jackson Warley · Tim Doster · Henry Kvinge 🔗 |
-
|
Solving Math Word Problems by Combining Language Models With Symbolic Solvers ( Poster ) > link | Joy He-Yueya · Gabriel Poesia · Rose Wang · Noah Goodman 🔗 |
-
|
WAMP: A Competition-Level Dataset for Assessing the Mathematical Reasoning Capabilities of LLMs ( Poster ) > link | Yujun Mao · Yoon Kim · Yilun Zhou 🔗 |
-
|
AI for Mathematics: A Cognitive Science Perspective ( Poster ) > link | Cedegao (Ced) Zhang · Katie Collins · Adrian Weller · Josh Tenenbaum 🔗 |
-
|
A Language-Agent Approach to Formal Theorem-Proving ( Poster ) > link | Amitayush Thakur · Yeming Wen · Swarat Chaudhuri 🔗 |
-
|
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts ( Poster ) > link | Pan Lu · Hritik Bansal · Tanglin Xia · Jiacheng Liu · Chunyuan Li · Hannaneh Hajishirzi · Hao Cheng · Kai-Wei Chang · Michel Galley · Jianfeng Gao 🔗 |
-
|
ToolDec: Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding ( Poster ) > link | Hongqiao Chen · Kexun Zhang · Lei Li · William Yang Wang 🔗 |
-
|
Teaching small transformers to rewrite ZX diagrams ( Poster ) > link | Francois Charton · Alexandre Krajenbrink · Konstantinos Meichanetzidis · Richie Yeung 🔗 |
-
|
Teaching Arithmetic to Small Transformers ( Poster ) > link | Nayoung Lee · Kartik Sreenivasan · Jason Lee · Kangwook Lee · Dimitris Papailiopoulos 🔗 |
-
|
Magnushammer: A Transformer-Based Approach to Premise Selection ( Poster ) > link | Maciej Mikuła · Szymon Antoniak · Szymon Tworkowski · Bartosz Piotrowski · Albert Q. Jiang · Jin Zhou · Christian Szegedy · Łukasz Kuciński · Piotr Miłoś · Yuhuai Wu 🔗 |
-
|
SIRD: Symbolic Integration Rules Dataset ( Poster ) > link | Vaibhav Sharma · Abhinav Nagpal · Muhammed Fatih Balin 🔗 |
-
|
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning ( Poster ) > link | Zhenwen Liang · Dian Yu · Xiaoman Pan · Wenlin Yao · Qingkai Zeng · Xiangliang Zhang · Dong Yu 🔗 |
-
|
Exploration with Principles for Diverse AI Supervision ( Poster ) > link | Hao Liu · Matei A Zaharia · Pieter Abbeel 🔗 |
-
|
EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning ( Poster ) > link | Raja Sekhar Reddy Mekala · Yasaman Razeghi · Sameer Singh 🔗 |
-
|
TinyGSM: achieving 80% on GSM8k with one billion parameters ( Poster ) > link | Bingbin Liu · Sebastien Bubeck · Ronen Eldan · Janardhan Kulkarni · Yuanzhi Li · Anh Nguyen · Rachel Ward · Yi Zhang 🔗 |
-
|
Basic Arithmetic Properties in the Space of Language Model Prompts ( Poster ) > link | Mateusz Krubiński 🔗 |
-
|
llmstep: LLM proofstep suggestions in Lean ( Poster ) > link | Sean Welleck · Rahul Saha 🔗 |
-
|
Lemur: Integrating Large Language Models in Automated Program Verification ( Oral ) > link | Haoze Wu · Clark Barrett · Nina Narodytska 🔗 |
-
|
Learning Multi-Step Reasoning by Solving Arithmetic Tasks ( Poster ) > link | Tianduo Wang · Wei Lu 🔗 |
-
|
Continual Learning and Out of Distribution Generalization in a Systematic Reasoning Task ( Poster ) > link | Mustafa Abdool · Andrew Nam · James McClelland 🔗 |
-
|
Vertical AI-driven Scientific Discovery ( Poster ) > link | Yexiang Xue 🔗 |
-
|
Spoken Language Understanding Evaluations for Home-Based Basic Math Learning ( Poster ) > link | Eda Okur · Saurav Sahay · Nachman 🔗 |
-
|
LLMs vs ITPs ( Poster ) > link | Simon Frieder · Martin Trimmel · Rashid Alawadhi · Klaus Gy 🔗 |
-
|
Towards Large Language Models as Copilots for Theorem Proving in Lean ( Poster ) > link | Peiyang Song · Kaiyu Yang · Animashree Anandkumar 🔗 |
-
|
CNN models' sensitivity to numerosity concepts ( Poster ) > link | Neha Upadhyay · Sashank Varma 🔗 |
-
|
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models ( Poster ) > link | Pan Lu · Baolin Peng · Hao Cheng · Michel Galley · Kai-Wei Chang · Ying Nian Wu · Song-Chun Zhu · Jianfeng Gao 🔗 |
-
|
SCIBENCH: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models ( Poster ) > link | Xiaoxuan Wang · Ziniu Hu · Pan Lu · Yanqiao Zhu · Jieyu Zhang · Satyen Subramaniam · Arjun Loomba · Shichang Zhang · Yizhou Sun · Wei Wang 🔗 |
-
|
SatLM: Satisfiability-Aided Language Models Using Declarative Prompting ( Poster ) > link | Xi Ye · Qiaochu Chen · Isil Dillig · Greg Durrett 🔗 |
-
|
ARB: Advanced Reasoning Benchmark for Large Language Models ( Poster ) > link | Tom Sawada · Daniel Paleka · Alexander Havrilla · Pranav Tadepalli · Paula Vidas · Alexander Kranias · John Nay · Kshitij Gupta · Aran Komatsuzaki 🔗 |
-
|
Learning the greatest divisor - Explainable predictions in transformers ( Oral ) > link | Francois Charton 🔗 |
-
|
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text - Poster ( Poster ) > link | Keiran Paster · Marco Dos Santos · Zhangir Azerbayev · Jimmy Ba 🔗 |
-
|
Solving Math Word Problems with Reexamination ( Poster ) > link | Yi Bin · WENHAO SHI · Yujuan Ding · Yang Yang · See-Kiong Ng 🔗 |
-
|
Discovering Lyapunov functions with transformers ( Poster ) > link | Alberto Alfarano · Francois Charton · Amaury Hayat 🔗 |
-
|
Llemma: An Open Language Model For Mathematics ( Poster ) > link | Zhangir Azerbayev · Hailey Schoelkopf · Keiran Paster · Marco Dos Santos · Stephen McAleer · Albert Q. Jiang · Jia Deng · Stella Biderman · Sean Welleck 🔗 |
-
|
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text - Oral ( Oral ) > link | 🔗 |
-
|
Understanding Length Generalization by Thinking Like Transformers - Oral ( Oral ) > link | 🔗 |
-
|
Lemur: Integrating Large Language Models in Automated Program Verification - Poster ( Poster ) > link | 🔗 |
-
|
Learning the greatest divisor - Explainable predictions in transformers - Poster ( Poster ) > link | 🔗 |