AsyncPatch Diffusion introduces asynchronous per-region noise levels in diffusion models, proves a valid ELBO, and uses a controlled sampler to support spatially adaptive generation and native inpainting.
Rolling diffusion models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Diffusion models have recently been increasingly applied to temporal data such as video, fluid mechanics simulations, or climate data. These methods generally treat subsequent frames equally regarding the amount of noise in the diffusion process. This paper explores Rolling Diffusion: a new approach that uses a sliding window denoising process. It ensures that the diffusion process progressively corrupts through time by assigning more noise to frames that appear later in a sequence, reflecting greater uncertainty about the future as the generation process unfolds. Empirically, we show that when the temporal dynamics are complex, Rolling Diffusion is superior to standard diffusion. In particular, this result is demonstrated in a video prediction task using the Kinetics-600 video dataset and in a chaotic fluid dynamics forecasting experiment.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Point-cloud skeleton conditions and a Reset-and-Roll inference scheme enable stable frame-wise autoregressive driving video generation for closed-loop autonomous driving simulation.
FacePlex introduces a unified streaming model with Rolling Flow Matching and Rolling Cross-Attention to enable full-duplex joint real-time generation of speech and facial motion tokens.
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
DVG-WM disentangles dynamics learning from visual synthesis via flow matching and latent degradation to deliver faster, higher-quality video predictions for robotic manipulation.
Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.
RecFM uses recursive self-consistency in flow matching to enable high-fidelity one- and few-step (2-4 step) generation of scientific dynamics, claiming 20x speedup over diffusion emulators and 15% lower MSE than vanilla flow matching.
Learned PDE solving should target transport over admissible futures via flow learners, not snapshot state regression.
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.
citing papers explorer
-
AsyncPatch Diffusion: spatially-flexible image generation
AsyncPatch Diffusion introduces asynchronous per-region noise levels in diffusion models, proves a valid ELBO, and uses a controlled sampler to support spatially adaptive generation and native inpainting.
-
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation
Point-cloud skeleton conditions and a Reset-and-Roll inference scheme enable stable frame-wise autoregressive driving video generation for closed-loop autonomous driving simulation.
-
FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars
FacePlex introduces a unified streaming model with Rolling Flow Matching and Rolling Cross-Attention to enable full-duplex joint real-time generation of speech and facial motion tokens.
-
AR Forcing: Towards Long-Horizon Robot Navigation World Model
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
DVG-WM disentangles dynamics learning from visual synthesis via flow matching and latent degradation to deliver faster, higher-quality video predictions for robotic manipulation.
-
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.
-
Recursive Flow Matching
RecFM uses recursive self-consistency in flow matching to enable high-fidelity one- and few-step (2-4 step) generation of scientific dynamics, claiming 20x speedup over diffusion emulators and 15% lower MSE than vanilla flow matching.
-
Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing
Learned PDE solving should target transport over admissible futures via flow learners, not snapshot state regression.
-
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.