SCALLOP replaces Hutchinson's trace estimator with a scalable, vectorized likelihood distillation objective for F2D2 flow maps, cutting training variance and time while improving performance on molecular Boltzmann generators and image data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
stNCE learns the energy of the joint density over data and time via spatiotemporal differences, unifies prior methods, and reports competitive performance on image and molecule density estimation.
citing papers explorer
-
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
SCALLOP replaces Hutchinson's trace estimator with a scalable, vectorized likelihood distillation objective for F2D2 flow maps, cutting training variance and time while improving performance on molecular Boltzmann generators and image data.
-
Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
stNCE learns the energy of the joint density over data and time via spatiotemporal differences, unifies prior methods, and reports competitive performance on image and molecule density estimation.