ArXiv TLDR

Tomaso Poggio

3 papers · Latest:

Artificial Intelligence

The Generalized Turing Test: A Foundation for Comparing Intelligence

The Generalized Turing Test (GTT) offers a formal, dataset-agnostic framework to compare AI agent intelligence via indistinguishability.

2605.10851
Machine Learning

Too Sharp, Too Sure: When Calibration Follows Curvature

This paper shows neural network calibration is tightly linked to training-time curvature and introduces a margin-aware objective for better calibration.

2604.20614
Machine Learning

Momentum Further Constrains Sharpness at the Edge of Stochastic Stability

SGD with momentum exhibits batch-size-dependent sharpness at the Edge of Stochastic Stability, favoring flatter regions at small batches and sharper at large.

2604.14108

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.