DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.
A lyapunov theory for the analysis of the global convergence of deep learning.arXiv preprint arXiv:2310.19702,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.