WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
hub
On the importance of noise scheduling for diffu- sion models
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
abstract
We empirically study the effect of noise scheduling strategies for denoising diffusion generative models. There are three findings: (1) the noise scheduling is crucial for the performance, and the optimal one depends on the task (e.g., image sizes), (2) when increasing the image size, the optimal noise scheduling shifts towards a noisier one (due to increased redundancy in pixels), and (3) simply scaling the input data by a factor of $b$ while keeping the noise schedule function fixed (equivalent to shifting the logSNR by $\log b$) is a good strategy across image sizes. This simple recipe, when combined with recently proposed Recurrent Interface Network (RIN), yields state-of-the-art pixel-based diffusion models for high-resolution images on ImageNet, enabling single-stage, end-to-end generation of diverse and high-fidelity images at 1024$\times$1024 resolution (without upsampling/cascades).
hub tools
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
SKILD unifies unconditional image generation and continuous super-resolution in one diffusion model via scale-invariant k-space dynamics where the reverse process handles both tasks by varying only the starting timestep.
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
Non-monotonic sampling schedules never improve upon monotonic baselines in diffusion models, with performance gaps ranging from substantial to negligible depending on the denoiser.
Proposes an advection-diffusion PDE corruption process with stochastic velocity fields and Lattice Boltzmann solver for diffusion models, generalizing prior PDE methods.
A generative model produces realistic and coherent 360 panoramic videos from in-the-wild perspective videos via curated online data and geometry-motion aware operations.
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
SteeringDRL identifies two optimization regimes in diffusion autoencoders and uses gated residual U-Nets with a log SNR curriculum to steer training toward disentangled representations, improving performance across multiple benchmarks.
Proposes CFRG noise schedule for diffusion models that assigns larger noises to low-frequency classes to improve generation on imbalanced datasets.
WavFlow performs direct waveform audio generation via flow matching on 2D token grids from raw patches plus amplitude lifting, matching latent-based methods on VGGSound and AudioCaps without intermediate compression.
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
NoiseShift learns a resolution-specific mapping from scheduler noise to conditioning noise via lightweight calibration to restore consistency and improve low-resolution generation quality in models like SD3 and Flux.
Zero123++ produces high-quality 3D-consistent multi-view images from a single input by fine-tuning Stable Diffusion with targeted conditioning and training methods.
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
citing papers explorer
-
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
-
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
SKILD unifies unconditional image generation and continuous super-resolution in one diffusion model via scale-invariant k-space dynamics where the reverse process handles both tasks by varying only the starting timestep.
-
Generative Pseudo-Force Fields for Molecular Generation
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
-
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\"odinger Samplers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
-
Is Monotonic Sampling Necessary in Diffusion Models?
Non-monotonic sampling schedules never improve upon monotonic baselines in diffusion models, with performance gaps ranging from substantial to negligible depending on the denoiser.
-
Beyond Blur: A Fluid Perspective on Generative Diffusion Models
Proposes an advection-diffusion PDE corruption process with stochastic velocity fields and Lattice Boltzmann solver for diffusion models, generalizing prior PDE methods.
-
Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos
A generative model produces realistic and coherent 360 panoramic videos from in-the-wild perspective videos via curated online data and geometry-motion aware operations.
-
History-Guided Video Diffusion
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
-
Steering Optimisation Trajectories in Diffusion Representation Learning
SteeringDRL identifies two optimization regimes in diffusion autoencoders and uses gated residual U-Nets with a log SNR curriculum to steer training toward disentangled representations, improving performance across multiple benchmarks.
-
Class-frequency Guided Noise Schedule for Diffusion Models
Proposes CFRG noise schedule for diffusion models that assigns larger noises to low-frequency classes to improve generation on imbalanced datasets.
-
WavFlow: Audio Generation in Waveform Space
WavFlow performs direct waveform audio generation via flow matching on 2D token grids from raw patches plus amplitude lifting, matching latent-based methods on VGGSound and AudioCaps without intermediate compression.
-
Back to Basics: Let Denoising Generative Models Denoise
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
-
NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation
NoiseShift learns a resolution-specific mapping from scheduler noise to conditioning noise via lightweight calibration to restore consistency and improve low-resolution generation quality in models like SD3 and Flux.
-
Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
Zero123++ produces high-quality 3D-consistent multi-view images from a single input by fine-tuning Stable Diffusion with targeted conditioning and training methods.
-
World Simulation with Video Foundation Models for Physical AI
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.