SGVF uses score-based generative models to create guiding vector fields from data distributions, enabling reliable robotic path following on complex, unordered, and branching topologies where classical methods fail.
Estimation of non-normalized statistical models by score matching,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.
citing papers explorer
-
Guiding Vector Field Generation via Score-based Diffusion Model
SGVF uses score-based generative models to create guiding vector fields from data distributions, enabling reliable robotic path following on complex, unordered, and branching topologies where classical methods fail.
-
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.