activity
20242026
collaborators

9 papers

cs.LG2026

Learning through Internalization

Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev +2

We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We in…

cs.LG2026

Learning to Think from Multiple Thinkers

Nirmit Joshi, Roey Magen, Nathan Srebro +2

We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step so…

cs.LG2025

How Reinforcement Learning After Next-Token Prediction Facilitates Learning

Nikolaos Tsilivis, Eran Malach, Karen Ullrich +1

Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the n…

cs.AI2025

OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability

Karen Ullrich, Jingtong Su, Claudia Shi +7

Reliability is key to realizing the promise of autonomous UI-Agents, multimodal agents that directly interact with apps in the same manner as humans, as users must be able to trust…

cs.LG2025

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks

Nikolaos Tsilivis, Eitan Gronich, Julia Kempe +1

We study the implicit bias of the general family of steepest descent algorithms with infinitesimal learning rate in deep homogeneous neural networks. We show that: (a) an algorithm…

cs.LG2024

On the Robustness of Neural Collapse and the Neural Collapse of Robustness

Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis +1

Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical…