Marco Mondelli

4

Papers

5

Total Citations

Papers (4)

Test-Time Training Provably Improves Transformers as In-context Learners

How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth