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 Baseline reference
arXiv preprint arXiv:2504.07963 (2025)
Baseline reference. 60% of citing Pith papers use this work as a benchmark or comparison.
29
Pith papers citing it
Baseline
60% of classified citations
hub tools
citation-role summary
baseline 3
background 2
citation-polarity summary
representative citing papers
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
AsymFlow uses rank-asymmetric velocity prediction to reach 1.57 FID on ImageNet 256x256 and enables finetuning of latent flow models into superior pixel-space text-to-image generators.
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample quality than fixed-representation baselines.
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
Representation Forcing lets a UMM decoder autoregressively predict its own understanding representations as in-context tokens that guide pixel-space diffusion, matching VAE-based generation without an external latent space.
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.
MIND integrates discrete patch tokenization into diffusion score functions via soft top-k and dual-branch layers, achieving FID 22.73 (no guidance) and 2.06 (with guidance) on ImageNet-256 after 80 epochs, outperforming DiT and larger LlamaGen models.
A pixel-space network that injects frozen DINOv3 semantic features through spatially continuous per-pixel modulation reports state-of-the-art PSNR/SSIM/LPIPS on LOLv2-Real (29.08/0.902/0.089) and the best average across four paired LLIE benchmarks.
A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.
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.
A learned 32-channel semantic compression lets a normalizing flow reach gFID 1.65 on ImageNet 256×256, the best FID reported for flow-based image generation.
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-image benchmarks.
PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and zero-shot conditional outputs.
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
x-prediction maintains manifold adherence during training-free diffusion guidance better than ε- or v-prediction, per theoretical analysis and experiments on bird classification and style transfer.
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.
-
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
-
Asymmetric Flow Models
AsymFlow uses rank-asymmetric velocity prediction to reach 1.57 FID on ImageNet 256x256 and enables finetuning of latent flow models into superior pixel-space text-to-image generators.
-
Coevolving Representations in Joint Image-Feature Diffusion
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample quality than fixed-representation baselines.
-
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.
-
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Representation Forcing lets a UMM decoder autoregressively predict its own understanding representations as in-context tokens that guide pixel-space diffusion, matching VAE-based generation without an external latent space.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.
-
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
MIND integrates discrete patch tokenization into diffusion score functions via soft top-k and dual-branch layers, achieving FID 22.73 (no guidance) and 2.06 (with guidance) on ImageNet-256 after 80 epochs, outperforming DiT and larger LlamaGen models.
-
PixIE: Prompted Pixel-Space Low-Light Image Enhancement
A pixel-space network that injects frozen DINOv3 semantic features through spatially continuous per-pixel modulation reports state-of-the-art PSNR/SSIM/LPIPS on LOLv2-Real (29.08/0.902/0.089) and the best average across four paired LLIE benchmarks.
-
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.
-
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.
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
A learned 32-channel semantic compression lets a normalizing flow reach gFID 1.65 on ImageNet 256×256, the best FID reported for flow-based image generation.
-
A Few-Step Generative Model on Cumulative Flow Maps
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
MotionHiFlow: Text-to-motion via hierarchical flow matching
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
-
Continuous Adversarial Flow Models
Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-image benchmarks.
-
Protein Autoregressive Modeling via Multiscale Structure Generation
PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and zero-shot conditional outputs.
-
PixelDiT: Pixel Diffusion Transformers for Image Generation
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
-
SURF: Signature-Retained Fast Video Generation
SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
-
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.
-
Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
x-prediction maintains manifold adherence during training-free diffusion guidance better than ε- or v-prediction, per theoretical analysis and experiments on bird classification and style transfer.
-
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Trajectory Forcing makes generative image synthesis trajectory-centric by organizing it into decodable semantic stages derived from clustered visual representations and trained with one-step flow-matching models.
-
FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
FrequencyBooster reports state-of-the-art FID scores of 1.60 at 256x256 and 1.69 at 512x512 for pixel diffusion by using a specialized decoder for full-frequency modeling.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix generates images by transporting low- and high-frequency wavelet components along separate schedules, reaching 1.91 FID on ImageNet 256×256.
-
HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
HyperDiT reports FID 1.56 on ImageNet 256x256 using hyper-connected cross-scale attention, SA-RoPE, and VFM registers in pixel space.