Binomial flows close the gap between continuous flow matching and discrete ordinal data by using binomial distributions to enable unified denoising, sampling, and exact likelihoods in diffusion models.
hub
Back to Basics: Let Denoising Generative Models Denoise
38 Pith papers cite this work. Polarity classification is still indexing.
38
Pith papers citing it
abstract
Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "Just image Transformers", or JiT, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data.
hub tools
citation-role summary
method 1
citation-polarity summary
claims ledger
- abstract Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimens
co-cited works
fields
cs.CV 17 cs.LG 8 cs.CL 3 cs.RO 2 cs.AI 1 cs.IR 1 eess.IV 1 eess.SP 1 eess.SY 1 physics.ao-ph 1years
2026 38verdicts
UNVERDICTED 38roles
method 1polarities
use method 1representative citing papers
A sparse voxel-space diffusion method with structure-adaptive modulation achieves up to 10x training speedup and state-of-the-art results for 3D medical image denoising and super-resolution.
Diffusion models show grokking on modular addition by composing periodic operand representations in simple data regimes or by separating arithmetic computation from visual denoising across timesteps in varied regimes.
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.
FARM is a foundation model combining masked autoencoders and diffusion decoders to estimate high-resolution aerial radio maps from a new multi-band low-altitude dataset, claiming superior accuracy and generalization over prior methods.
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.
L2P repurposes pre-trained LDMs for direct pixel generation via large-patch tokenization and shallow-layer training on synthetic data, matching source performance with 8-GPU training and enabling native 4K output.
BitLM replaces per-token softmax with bitwise continuous diffusion inside causal blocks to generate multiple tokens in parallel while preserving autoregressive structure.
A multivariate diffusion generative downscaling method preserves inter-variable correlations in climate data under large resolution increases, enabling more accurate compound risk assessment.
ELF is a continuous embedding-space flow matching model for language that stays continuous until the last step and outperforms prior discrete and continuous diffusion language models with fewer sampling steps.
A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.
Smaller end-to-end autonomous driving models achieve optimal 3-second trajectory prediction accuracy at lower or intermediate temporal sampling frequencies, whereas larger VLA-style models perform best at the highest frequencies across Waymo, nuScenes, and PAVE datasets.
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
Outlier tokens in DiTs are addressed with Dual-Stage Registers, which reduce artifacts and improve image generation on ImageNet and text-to-image tasks.
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.
MSDiff maps degraded hyperspectral data to a low-dimensional manifold and uses diffusion to regularize features for more robust classification under complex degradations.
CoreFlow is a low-rank matrix generative model that trains normalizing flows on shared subspaces to improve efficiency and quality for high-dimensional limited-sample data, including incomplete matrices.
V-GRPO makes ELBO surrogates stable and efficient for online RL alignment of denoising models, delivering SOTA text-to-image performance with 2-3x speedups over MixGRPO and DiffusionNFT.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
VOLT is a probabilistic transport method with a 3D anisotropic network that improves wide-field microscopy volume reconstruction in lateral and axial directions while supplying voxel-wise credibility estimates.
RF-CMG synthesizes high-quality mmWave and RFID signals from WiFi using a diffusion model with Modality-Guided Embedding for high-frequency details and Low-Frequency Modality Consistency to preserve physical structure.
GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.
FeaXDrive improves end-to-end autonomous driving by shifting diffusion planning to a trajectory-centric formulation with curvature-constrained training, drivable-area guidance, and GRPO post-training, yielding stronger closed-loop performance and feasibility on NAVSIM.
CoD-Lite delivers real-time generative image compression via a lightweight convolution-based diffusion codec with compression-oriented pre-training and distillation, achieving substantial bitrate savings.
citing papers explorer
-
Binomial flows: Denoising and flow matching for discrete ordinal data
Binomial flows close the gap between continuous flow matching and discrete ordinal data by using binomial distributions to enable unified denoising, sampling, and exact likelihoods in diffusion models.
-
Grokking of Diffusion Models: Case Study on Modular Addition
Diffusion models show grokking on modular addition by composing periodic operand representations in simple data regimes or by separating arithmetic computation from visual denoising across timesteps in varied regimes.
-
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.
-
CoreFlow: Low-Rank Matrix Generative Models
CoreFlow is a low-rank matrix generative model that trains normalizing flows on shared subspaces to improve efficiency and quality for high-dimensional limited-sample data, including incomplete matrices.
-
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
V-GRPO makes ELBO surrogates stable and efficient for online RL alignment of denoising models, delivering SOTA text-to-image performance with 2-3x speedups over MixGRPO and DiffusionNFT.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing
RF-CMG synthesizes high-quality mmWave and RFID signals from WiFi using a diffusion model with Modality-Guided Embedding for high-frequency details and Low-Frequency Modality Consistency to preserve physical structure.
-
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.