activity
20172026
most citedEmerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

18 citations · 43 across the 10 of their papers we have counts for

collaborators

21 papers

cs.LG2026

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

Achleshwar Luthra, Yash Salunkhe, Tomer Galanti

Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, \emph{directional} CDNV (de…

cs.LG2025

Scalable Principal-Agent Contract Design via Gradient-Based Optimization

Tomer Galanti, Aarya Bookseller, Korok Ray

We study a bilevel \emph{max-max} optimization framework for principal-agent contract design, in which a principal chooses incentives to maximize utility while anticipating the age…

cs.LG2025

On the Alignment Between Supervised and Self-Supervised Contrastive Learning

Achleshwar Luthra, Priyadarsi Mishra, Tomer Galanti

Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent…

cs.LG2025

Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning

Achleshwar Luthra, Tianbao Yang, Tomer Galanti

Despite its empirical success, the theoretical foundations of self-supervised contrastive learning (CL) are not yet fully established. In this work, we address this gap by showing…

cs.LG2025

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

Gang Li, Ming Lin, Tomer Galanti +2

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning…

cs.CL2024

The Fair Language Model Paradox

Andrea Pinto, Tomer Galanti, Randall Balestriero

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on ag…