2 papers
cs.LG2026
On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers
Sixu Li, Thomas Jacob Maranzatto, Jan Peszek +5
We study the inference-time behavior of deep linear encoder-only transformers through the lens of interacting particle systems. In this perspective, tokens are modeled as particles…
math.AP2024
Alignment with nonlinear velocity couplings: collision-avoidance and micro-to-macro mean-field limits
Young-Pil Choi, MichaÅ Fabisiak, Jan Peszek
We investigate the pressureless fractional Euler-alignment system with nonlinear velocity couplings, referred to as the -Euler-alignment system. This model features a nonlinear…