Signals 4 · free daily AI digest

Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning

Paper recorded by Signals 4 on 2026-09-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-01 on arXiv · recorded by Signals 4 on 2026-09-02

Category: cs.LG · 机器学习 · first seen 2026-09-02

Abstract

Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that can be run to arbitrary depth. The result is an anytime solver: accuracy keeps improving with inference depth far beyond the rollout lengths and backp

Read on arXiv →

#165 most recent of 215 cs.LG papers we have recorded · ↑ newer: Does Imitation Learning Preserve Temporal Robustness in Dexterous Mani · ↓ older: Edge-Girth as a Structural Edge Feature for Graph Neural Networks
Cite this page: Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning: the #165 most recent of 215 cs.LG papers we have recorded (as of 2026-09-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/diffusion-as-a-training-curriculum-for-timestep-free-iterative-reasoning.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG 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