arXiv Machine Learning
Controlling Polar Exposure to Delay Memorization in Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 26
Delayed Optimizer-State Transport Shapes Short-Horizon Training Decisions
arXiv:2608.24593v1 Announce Type: new Abstract: Adaptive optimizers retain gradient history in moment variables, allowing a local change in loss weighting to alter later updates. We examine whether t...
arXiv Computer Vision
Sep 1
Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling
arXiv:2608.29322v1 Announce Type: new Abstract: Recent video diffusion models have achieved remarkable generation quality, but high-fidelity results still largely depend on closed-source systems or c...
arXiv Machine Learning
Jun 30
ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies
arXiv:2606. 28939v1 Announce Type: new Abstract: Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure.
arXiv AI
Aug 14
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.
arXiv Computer Vision
Sep 3
SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
SelfLift is a progressive‑resolution framework that accelerates few‑step diffusion models by enabling late, self‑recovering transitions between low‑ and high‑resolution latents. It introduces a training‑free Artifact‑Aware Consistency Lift that uses disagreement between direct latent lifting and pixel‑VAE re‑encoding to detect and correct artifacts, and a self‑recovery policy that transfers high‑resolution guidance from an internal teacher. Experiments on FLUX.2‑Klein and Z‑Image‑Turbo show latency reductions of 41.5% and 44.1%, and overall speedups of 29.61× and 19.21× over 50‑step baselines while maintaining competitive generation quality.
arXiv AI
5d ago
Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
The paper investigates reinforcement learning with verifiable rewards (RLVR), where costly model-generated responses encourage larger rollout batches and a square‑root learning‑rate scaling. Using a two‑clock framework, the authors show that while the square‑root rule preserves first‑order drift per sample, larger batches suffer from curvature losses, leading to a critical batch size beyond which sample efficiency degrades. Experiments on Qwen2.5‑Math‑1.5B confirm the predicted progress gap and failure clock, and the authors propose a simple multi‑step RLVR schedule that starts below the critical batch and switches to a larger batch before failure.