Boix-Adserà, Enric

8 publications

NeurIPS 2025 Let Me Think! a Long Chain of Thought Can Be Worth Exponentially Many Short Ones Parsa Mirtaheri, Ezra Edelman, Samy Jelassi, Eran Malach, Enric Boix-Adserà

ICLR 2024 When Can Transformers Reason with Abstract Symbols? Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind

TMLR 2023 Tight Conditions for When the NTK Approximation Is Valid Enric Boix-Adserà, Etai Littwin

NeurIPS 2023 Transformers Learn Through Gradual Rank Increase Enric Boix-Adsera, Etai Littwin, Emmanuel Abbe, Samy Bengio, Joshua Susskind

NeurIPS 2022 GULP: A Prediction-Based Metric Between Representations Enric Boix-Adsera, Hannah Lawrence, George Stepaniants, Philippe Rigollet

NeurIPS 2022 On the Non-Universality of Deep Learning: Quantifying the Cost of Symmetry Emmanuel Abbe, Enric Boix-Adsera

NeurIPS 2021 The Staircase Property: How Hierarchical Structure Can Guide Deep Learning Emmanuel Abbe, Enric Boix-Adsera, Matthew S Brennan, Guy Bresler, Dheeraj Nagaraj

JMLR 2021 Wasserstein Barycenters Can Be Computed in Polynomial Time in Fixed Dimension Jason M Altschuler, Enric Boix-Adsera