A Markov category framework for language models provides an information-theoretic rationale for speculative decoding and shows that a quadratic surrogate to negative log-likelihood induces generalized CCA alignment in linear-softmax heads after normalization.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Two MCMC algorithms for latent position models with almost O(|E|) and O(|V|) running times plus stronger accuracy guarantees than Rastelli et al. (2024).
MDL-GBTRSC builds an MDL-selected granular-ball tree to regularize affinity graphs in spectral clustering and reports top average ARI and NMI versus baselines.
citing papers explorer
-
A Markov Categorical Framework for Language Modeling
A Markov category framework for language models provides an information-theoretic rationale for speculative decoding and shows that a quadratic surrogate to negative log-likelihood induces generalized CCA alignment in linear-softmax heads after normalization.
-
Accurate and Efficient MCMC for Latent Position Models
Two MCMC algorithms for latent position models with almost O(|E|) and O(|V|) running times plus stronger accuracy guarantees than Rastelli et al. (2024).
-
Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering
MDL-GBTRSC builds an MDL-selected granular-ball tree to regularize affinity graphs in spectral clustering and reports top average ARI and NMI versus baselines.