About & Research

We are the Deep Learning Fundamentals group at Texas A&M, led by Prof. Tomer Galanti. We connect rigorous theory with practical algorithms to understand and improve modern deep learning and large language models.

Theory of LLM reasoning: Which architectures, objectives, and training procedures reliably improve multi-step reasoning in LLMs?
  • Auto-regressive decision trees [1]
  • DisCO: constrained optimization for reasoning [1]
  • Rare-token depreciation bias [1]
Deep representation learning: What representations do neural networks actually learn, and which ones support strong generalization?
  • Low-rank bias [1]
  • Understanding supervised pre-training [1, 2, 3]
  • Understanding self-supervised pre-training [1, 2]
  • The canonical representation hypothesis (CRH) [1]
  • Intermediate neural collapse [1, 2]
Differentiable contract design: How can we apply modern optimization techniques to tackle fundamental challenges in contract and incentive design when closed-form solutions are unavailable?
  • Gradient-based optimization for contract design [1]

See the full list of publications.

Contact: galanti@tamu.edu  ·  GitHub: DLFundamentals  ·  Google Scholar: Profile
Texas A&M University · Department of Computer Science & Engineering

Group

Join the Lab

PhD applicants: Apply through the TAMU CSE PhD program. In your statement, describe your fit with our research areas and mention Prof. Galanti as a potential advisor.

Master's & undergraduates: We welcome motivated undergraduate and Master's students to volunteer for research. Please email a short CV, transcripts, and a paragraph about your interests and skills.

Teaching

Special Topics in Recent Developments in Deep Learning and Large Language Models
Texas A&M University, Fall 2025.

Introduction to Machine Learning
Texas A&M University, Spring 2025.

Special Topics in Recent Developments in Deep Learning and Large Language Models
Texas A&M University, Fall 2024.

Statistical Learning Theory and its Applications
Massachusetts Institute of Technology, Fall 2023.

Statistical Learning Theory and its Applications
Massachusetts Institute of Technology, Fall 2022.

Deep Convolutional Neural Networks
Tel Aviv University, Spring 2020.

Deep Convolutional Neural Networks
Tel Aviv University, Spring 2019.

↑ Top