clustering 1dynamic mode decomposition 1expectation-maximization 1koopman operators 1time-series prediction 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Cluster-Weighted EDMD
Lorenzo Tomaz, Judd Rosenblatt, Flavio Kicis +2
The paper proposes Cluster-Weighted EDMD, a method that learns both a soft partition of the state space and separate EDMD operators for each cluster, improving prediction accuracy…
cs.CL2025
Momentum Point-Perplexity Mechanics in Large Language Models
Lorenzo Tomaz, Judd Rosenblatt, Thomas Berry Jones +1
We take a physics-based approach to studying how the internal hidden states of large language models change from token to token during inference. Across 20 open-source transformer…