Submitted by Nandan Kumar Jha 5 Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws New York University 1
Submitted by Nandan Kumar Jha 3 Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space? New York University 2
3 Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies New York University