Signals 4 · free daily AI digest

Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport

Paper recorded by Signals 4 on 2026-09-10 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.AI · 人工智能 · first seen 2026-09-11

Abstract

Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain strong baselines but remains model-agnostic and ignores prediction error. Here we introduce a model-aware schedule construction based on fiberwise optimal trans

Read on arXiv →

#114 most recent of 300 cs.AI papers we have recorded · ↑ newer: From Parameters to Answers: How LLMs Retrieve and Use Their Internal K · ↓ older: Understanding Operator Attitudes Toward AI-Supported Decision Making i
Cite this page: Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport: the #114 most recent of 300 cs.AI papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/model-aware-schedules-improve-generation-via-fiberwise-optimal-transport.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions