Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
Teoria statistica delle classi e calcolo delle probabilita.Pubblicazioni del R istituto superiore di scienze economiche e commericiali di firenze, 8:3–62
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2roles
method 1polarities
use method 1representative citing papers
LaTA delivers a drop-in, FERPA-compliant local-LLM autograder for LaTeX-based STEM assignments that achieved 0.02-0.04% per-item error and correlated with 8-11% exam gains plus large confidence increases in a 200-student university course.
citing papers explorer
-
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.