Publications

Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning

A. Luthra*, Y. Salunkhe*, T. Galanti*

Preprint, arXiv, 2026

Tool Building as a Path to "Superintelligence"

D. Koplow, T. Galanti, T. Poggio

Preprint, arXiv, 2026

Scalable Principal–Agent Contract Design via Gradient-Based Optimization

T. Galanti, A. Bookseller, K. Ray

Preprint, arXiv, 2025

LLM Priors for ERM over Programs

S. Singhal, P. Mishra, E. Malach, T. Galanti

Preprint, arXiv, 2025

The Fair Language Model Paradox

A. Pinto, T. Galanti, R. Balestriero

Preprint, arXiv, 2024

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent

L. Ziyin, B. Li, T. Galanti, M. Ueda

Preprint, arXiv, 2023

Generalization Bounds for Transfer Learning with Pretrained Classifiers

T. Galanti, A. Gyorgy, M. Hutter

Preprint, arXiv, 2022

On the Alignment Between Supervised and Self-Supervised Contrastive Learning

A. Luthra, P. Mishra, T. Galanti

ICLR, 2026

Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning

A. Luthra, T. Yang, T. Galanti

NeurIPS, 2025

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

G. Li, M. Lin, T. Galanti, Z. Tu, T. Yang

NeurIPS, 2025

Formation of Representations in Neural Networks

L. Ziyin, I. L. Chuang, T. Galanti, T. Poggio

ICLR, 2025 Spotlight

Distributed Speculative Inference (DSI)

N. Timor, J. Mamou, D. Korat, M. Berchansky, O. Pereg, M. Wasserblat, T. Galanti, M. Gordon, D. Harel

ICLR, 2025

SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network

T. Galanti, Z. Siegel, A. Gupte, T. Poggio

CPAL, 2025 · NeurIPS M3L Workshop, 2024

On the Power of Decision Trees in Auto-Regressive Language Modeling

Y. Gan, T. Galanti, T. Poggio, E. Malach

NeurIPS, 2024

Norm-Based Generalization Bounds for Sparse Neural Networks

T. Galanti, M. Xu, L. Galanti, T. Poggio

NeurIPS, 2023

Reverse Engineering Self-Supervised Learning

I. Ben-Shaul, R. Shwartz-Ziv*, T. Galanti*, S. Dekel, Y. LeCun

NeurIPS, 2023

Comparative Generalization Bounds for Deep Neural Networks

T. Galanti, L. Galanti, I. Ben-Shaul

TMLR, 2023

Feature Learning in Deep Classifiers Through Intermediate Neural Collapse

A. Rangamani, M. Lindegaard, T. Galanti, T. Poggio

ICML, 2023

Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions

I. Ben-Shaul, T. Galanti, S. Dekel

TMLR, 2023

Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models

C. Xu, S. Yang, T. Galanti, B. Wu, X. Yue, B. Zhai, W. Zhan, P. Vajda, K. Keutzer, M. Tomizuka

ECCV, 2022

On the Role of Neural Collapse in Transfer Learning

T. Galanti, A. Gyorgy, M. Hutter

ICLR, 2022

Meta Internal Learning

R. Ben Sadoun, S. Gur, T. Galanti, L. Wolf

NeurIPS, 2021

On Random Kernels of Residual Architectures

E. Littwin*, T. Galanti*, L. Wolf

UAI, 2021

Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs

T. Galanti, S. Benaim, L. Wolf

JMLR, 2021

Evaluation Metrics for Conditional Image Generation

Y. Benny, T. Galanti, S. Benaim, L. Wolf

IJCV, 2021

On the Modularity of Hypernetworks

T. Galanti, L. Wolf

NeurIPS, 2020 Oral

On Infinite-Width Hypernetworks

E. Littwin*, T. Galanti*, L. Wolf

NeurIPS, 2020

Domain Intersection and Domain Difference

S. Benaim, M. Khaitov, T. Galanti, L. Wolf

ICCV, 2019

Unsupervised Learning of the Set of Local Maxima

L. Wolf, S. Benaim, T. Galanti

ICLR, 2019

Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

O. Press, T. Galanti, S. Benaim, L. Wolf

ICLR, 2019

Estimating the Success of Unsupervised Image to Image Translation

S. Benaim*, T. Galanti*, L. Wolf

ECCV, 2018

The Role of Minimal Complexity in Unsupervised Learning of Semantic Mappings

T. Galanti, L. Wolf, S. Benaim

ICLR, 2018

Gradient-Based Bilevel Optimization for Principal–Agent Contract Design

A. Bookseller, K. Ray, T. Galanti

NeurIPS Workshop: Generative AI in Finance, 2025

Distributed Speculative Inference of Large Language Models is Provably Faster

N. Timor, J. Mamou, D. Korat, M. Berchansky, O. Pereg, M. Wasserblat, T. Galanti, M. Gordon, D. Harel

NeurIPS ENLSP Workshop, 2024 (PMLR)

Dynamics of Deep Classifiers Trained with the Square Loss

M. Xu, A. Rangamani, Q. Liao, T. Galanti, T. Poggio

Research (A Science Partner Journal), 2023

Improved Generalization Bounds for Transfer Learning via Neural Collapse

T. Galanti, A. Gyorgy, M. Hutter

ICML Workshop on Pretraining, 2022

On the Implicit Bias Towards Depth Minimization in Deep Neural Networks

T. Galanti, L. Galanti, I. Ben-Shaul

DEEPMATH, 2022 · TOPML, 2022

Weakly Supervised Discovery of Semantic Attributes

A. A. Ali, T. Galanti, E. Zheltonozhskii, C. Baskin, L. Wolf

CLeaR, 2022

A Formal Approach to Explainability

L. Wolf, T. Galanti, T. Hazan

AIES, 2019

Generalization Bounds for Cross-Domain Mapping with WGANs

T. Galanti, S. Benaim, L. Wolf

NeurIPS Workshop on Integration of Deep Learning Theories, 2018

A Theoretical Framework for Deep Transfer Learning

T. Galanti, T. Hazan, L. Wolf

Information and Inference: A Journal of the IMA, 2016