Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow

arXiv:2610.20071 · cs.LG, cs.AI · Submitted 2026-10-14 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 36 pages, including appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decoupling — 1× in this paper · explained in 2 episodes

Sources

• Three Creates All: You Only Sample 3 Steps
• Mean Flows for One-step Generative Modeling
• Flow Map Language Models: One-step Language Modeling via Continuous Denoising
• Flow Matching for Generative Modeling
• DINOv2: Learning Robust Visual Features without Supervision
• Optimal Stepsize for Diffusion Sampling
• IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
• Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks