arXiv AI
Jul 28
CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion
arXiv:2607. 23159v1 Announce Type: new Abstract: Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more.
Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
Related stories
arXiv AI
Aug 18
Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
arXiv:2412. 18911v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs.
arXiv Machine Learning
Sep 22
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
arXiv:2602.24208v2 Announce Type: replace-cross Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequenti...
arXiv Machine Learning
Aug 3
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv Machine Learning
Jul 31
FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
arXiv:2607. 27842v1 Announce Type: cross Abstract: Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive.
arXiv AI
Jul 1
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
arXiv:2606. 31026v1 Announce Type: cross Abstract: We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction.
arXiv Machine Learning
Jun 26
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
arXiv:2606. 26778v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs.
arXiv AI
Oct 1
The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introdu...
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 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 Machine Learning
Jul 28
Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
arXiv:2604. 22901v2 Announce Type: replace Abstract: Diffusion models achieve remarkable success in time series generation.
arXiv Machine Learning
Sep 22
Optimizers for Diffusion Models: A Controlled Benchmark
The paper introduces the first controlled benchmark for optimizers in discrete diffusion models, evaluating seven optimizers (AdamW, Lion, Muon, SOAP, MARS, MARS‑M, Schedule‑Free) across four diffusion formulations: masked diffusion on text8, uniform diffusion on QM9 and LM1B, and Gaussian diffusion on CelebA‑64. Each optimizer undergoes the same search protocol and is retrained with full budget and multiple seeds, revealing that AdamW, while strong, is not universally optimal and that optimizers validated on autoregressive language models (Muon, MARS‑M, SOAP) can outperform tuned AdamW on certain tasks.