Nate S. Woodward

Nate S. Woodward

ML & Theoretical Physics PhD student at UW - Madison, MIT Math & Physics '25

Talks and presentations

LITP Spring Symposium: Fine-Tuning Small Reasoning Models for Quantum Field Theory

May 20, 2026

Talk, The 11th LITP Spring Symposium: Theoretical Physics and AI, Room 340, West Hall

Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability develops while training these models. To investigate this, we perform the first academic fine-tuning study of small (7B-parameter) reasoning models dedicated specifically to theoretical physics. Selecting Quantum Field Theory (QFT) as our primary domain, we developed a robust data generation pipeline to create synthetic problems and adapt existing human-authored problems for training, generating over 2,500 synthetic problems alongside a curated collection of human-adapted problems. We conduct both Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) experiments, benchmark performance gains and generalization to other physics domains, and analyze how reasoning errors evolve during training.

Bites of Foundation Models for Science: Product Manifold Machine Learning for Physics

November 20, 2024

Talk, Bites of Foundation Models for Science - Physics-inspired representaions, MIT

Particle jets exhibit tree-like structures through stochastic showering and hadronization. The hierarchical nature of these structures aligns naturally with hyperbolic space, a non-Euclidean geometry that captures hierarchy intrinsically. Drawing upon the foundations of geometric learning, we introduce hyperbolic transformer models tailored for tasks relevant to jet analyses, such as classification and representation learning. Through jet embeddings and jet tagging evaluations, our hyperbolic approach outperforms its Euclidean counterparts. These findings underscore the potential of using hyperbolic geometric representations in advancing jet physics analyses.

IAIFI Thematic Discussion on Representation and Manifold Learning: Product Manifold Machine Learning for Physics

October 18, 2024

Talk, IAIFI Thematic Discussion on Representation and Manifold Learning., MIT

Many of the recent successes in AI rely on the manifold hypothesis: that most high-dimensional data lie on a lower-dimensional manifold. From transfer to contrastive learning to foundation modeling, significant effort has been devoted to methods to efficiently find and map input data to this latent space. In this Thematic Discussion Session, we’ll hear from three distinguished speakers on extracting meaningful latent representations from data from the physical sciences: Aizhan Akhmetzhanova (Self-Supervised Learning for Data Compression and Inference in Cosmology), Nate Woodward, (Product Manifold Machine Learning for Physics) and David Baek, (GenEFT: Physics-Inspired Theory of Representation Learning). After three 10-minute lightning talks, we’ll have a 30 minute open discussion/Q&A session to explore the major challenges and opportunities in this field. We encourage attendees to come with questions and insights from their own work!

ML4Jets 2023: Hyperbolic Machine Learning for Physics

November 06, 2023

Talk, ML4Jets 2023, Hamburg, Germany

Particle jets exhibit tree-like structures through stochastic showering and hadronization. The hierarchical nature of these structures aligns naturally with hyperbolic space, a non-Euclidean geometry that captures hierarchy intrinsically. Drawing upon the foundations of geometric learning, we introduce hyperbolic transformer models tailored for tasks relevant to jet analyses, such as classification and representation learning. Through jet embeddings and jet tagging evaluations, our hyperbolic approach outperforms its Euclidean counterparts. These findings underscore the potential of using hyperbolic geometric representations in advancing jet physics analyses.