Tommy He

[email] [github] [linkedin]

I'm interested in improving our understanding of machine learning systems and their generalization capabilities including:

• Interpretability: mechanistic interpretability, representation analysis, attribution methods
• Open-ended learning: self-play, open-endedness, unsupervised RL
• Mathematical foundations of ML: geometry of learning, optimization, deep learning theory

Previously, I was a YC founder at Clarum, building AI agents for private capital investing. I've also worked on high frequency trading at Tower Research and privacy preserving knowledge intersection at Optable.

Research

• Context–Answer Metamodels: Forecasting LLM Activations Before the First Answer Token (2026)
  Tommy He, Thomas Jiralerspong
  NeurIPS 2026 NeuralArtifacts (oral spotlight)
  [paper] [code]
• tufazip (2026)
  Tommy He
  Large Text Compression Benchmark (#2)
  [blog] [code] [benchmark]
• A Predictive Law for On-Policy Self-Distillation From World Feedback (2026)
  Tommy He, Jerome Sieber^*, Matteo Saponati^*
  ICML 2026 RLxF
  [arxiv] [code]

Writings

• Overview of Isogeny Based Cryptography [pdf]
• Security is not Well-Defined [pdf]
• Theory of Machine Learning [pdf]
• Introduction to Algebraic Geometry [pdf]