Enric Boix

• Daniel Beaglehole, Adityanarayanan Radhakrishnan, Enric Boix, Mikhail Belkin (2026), Toward universal steering and monitoring of AI models, Science, 391 (6787), pp. 787-792.
• Enric Boix, Neil Mallinar, James B. Simon, Mikhail Belkin (Under Review), FACT: the Features At Convergence Theorem for neural networks.
• Parsa Mirtaheri, Ezra Edelman, Samy Jelassi, Eran Malach, Enric Boix (Under Review), Let Me Think! A long chain of thought can be worth exponentially many short ones.
• Enric Boix and Philippe Rigollet (Under Review), The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts.
• Enric Boix (Under Review), On the inductive bias of infinite-depth ResNets and the bottleneck rank.
• Rimon Melamed, Lucas Hurley McCabe, Tanay Wakhare, Yejin Kim, H. Howie Huang, Enric Boix (2024), Prompts have evil twins, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
• Enric Boix, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua Susskind (2024), When can transformers reason with abstract symbols?, International Conference on Representation Learning (ICLR).
• Enric Boix (Under Review), Towards a theory of model distillation.
• Enric Boix, Etai Littwin, Emmanuel Abbe, Samy Bengio, Joshua Susskind (2023), Transformers learn through gradual rank increase, Advances in Neural Information Processing Systems 36 (NeurIPS 2023).
• Enric Boix and Etai Littwin (2023), Tight conditions for when the NTK approximation is valid, Transactions on Machine Learning Research.
• All Research from Enric Boix »

Past Courses

• AMCS9950 - Dissertation

  Allows for a PhD student to be enrolled full-time to work exclusively on research, writing and preparing his/her doctoral thesis and defense. All required coursework (20 CUs) must be completed, and the student must have passed his/her thesis proposal/oral candidacy examination prior to being enrolled.

• AMCS9999 - Ind Study & Research

  Study under the direction of a faculty member.

• STAT4850 - Foundations of Deep Learning

  This course serves as a first, conceptual introduction to Deep Learning, which is the technology at the heart of modern AI. Topics include: what is a neural network and how to train it, generative AI, failure modes and safety of deep learning, and efficient deep learning.

• STAT5850 - Foundations of Deep Learning

  This course serves as a first, conceptual introduction to Deep Learning, which is the technology at the heart of modern AI. Topics include: what is a neural network and how to train it, generative AI, failure modes and safety of deep learning, and efficient deep learning. Prerequisites: Calculus, beginner programming experience with Python. Highly recommended: basic linear algebra (matrices and matrix multiplication).

• STAT9910 - Sem in Adv Appl of Stat

  This seminar is for graduate students who wish to learn about current research frontiers. It covers advanced topics in probability, statistical theory and methods, applied statistics, data science and artificial intelligence. Specific topics vary from year to year and emphasize both theoretical foundations and applications.

Knowledge @ Wharton

• Does Your Insurance Protect You From Climate Risk?, Knowledge @ Wharton - 05/19/2026
• Should AI Nudge You or Tell You What to Do?, Knowledge @ Wharton - 05/19/2026
• How Rwanda Is Using Drones to Improve Health Care, Knowledge @ Wharton - 05/19/2026
• AI’s Real Impact on Jobs and Productivity, Knowledge @ Wharton - 05/15/2026
• Career Growth, Job Mobility, and the Modern Workforce, Knowledge @ Wharton - 05/13/2026
• How Advanced Analytics Are Changing Professional Hockey, Knowledge @ Wharton - 05/13/2026
• AI’s Supply Chain Problem, Knowledge @ Wharton - 05/12/2026
• Lasting Loyalty: Why ‘Unreasonable Hospitality’ Wins, Knowledge @ Wharton - 05/12/2026
• Why Leadership Changes Often Backfire, Knowledge @ Wharton - 05/12/2026
• Rethinking Urban Tax Policy Through Land Value Taxation, Knowledge @ Wharton - 05/08/2026