arXiv AI
Jul 14
MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
arXiv:2512. 19311v2 Announce Type: replace-cross Abstract: This paper studies the training-testing discrepancy (a.
PEEK: One-Step-Look-Ahead Exposure Bias Correction for Diffusion Sampling
The paper introduces PEEK, a training‑free deterministic sampler plugin that corrects exposure bias in diffusion image generators by performing a provisional one‑step update and interpolating between predictions at a look‑ahead state. PEEK evaluates the denoiser at this higher‑signal noisy state, thereby producing more image‑like predictions and reducing the train‑test gap that often leads to blurry or poorly detailed outputs. Experiments on eight pixel‑space and latent‑space diffusion models—including unconditional, label‑guided, and text‑guided settings—show consistent improvements over NFE‑matched baselines, with FID gains up to 49.3 % and minimal additional computation.
Related stories
arXiv AI
Oct 15
Correction Training for Diffusion Models
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
arXiv AI
Sep 1
Training-Free Hidden-State Refinement for Flow-Matching Image Generators
arXiv:2608.29160v1 Announce Type: cross Abstract: We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the ou...
arXiv Machine Learning
Sep 30
Improved Distributional Diffusion Models
arXiv:2609.37147v1 Announce Type: cross Abstract: Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a \emph{distributional} denoiser trained via a scoring rule...
arXiv AI
Oct 27
SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
arXiv:2610.25844v2 Announce Type: replace-cross Abstract: Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this wo...
arXiv AI
Aug 12
SynBoost: A Synergistic Framework for Fast Sampling of Diffusion Models
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
arXiv AI
Aug 6
AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers
arXiv:2602. 13357v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure.
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
Jun 16
Region-Adaptive Sampling for Diffusion Transformers
arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.
arXiv AI
Jun 29
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
arXiv:2606. 27978v1 Announce Type: cross Abstract: Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches, avoiding discrete tokenization or a separately pretrained tokenizer.
arXiv Computer Vision
Sep 2
ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware
arXiv:2609.00955v1 Announce Type: new Abstract: Diffusion models achieve strong image generation quality but incur high iterative denoising costs. Analog compute-in-memory (CIM) can accelerate matrix...
arXiv AI
Oct 15
TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative Sampling
arXiv:2610.14332v1 Announce Type: cross Abstract: Accurate sampling from continuous-time generative models can require many model evaluations. Low-step sampling reduces cost, but coarse updates intro...