Causal Diffusion Model is the first diffusion-based method to produce full probabilistic counterfactual outcome distributions for sequential interventions in longitudinal data, showing 15-30% better distributional accuracy than prior methods on a tumor-growth simulator.
hub Mixed citations
Improved Denoising Diffusion Probabilistic Models
Mixed citation behavior. Most common role is background (33%).
26
Pith papers citing it
Background
33% of classified citations
abstract
Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs and GANs cover the target distribution. Finally, we show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable. We release our code at https://github.com/openai/improved-diffusion
hub tools
citation-role summary
background 3
baseline 3
method 2
dataset 1
citation-polarity summary
representative citing papers
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
Monte Carlo and ML surrogate framework projects PTA sensitivity to compact DM substructures and shows SGWB weakens it, with only Shapiro searches retaining sensitivity in optimistic cases.
REPA-P aligns intermediate representations in diffusion models with physical states using first-principles PDE residuals to accelerate convergence and boost out-of-distribution robustness on PDE tasks.
GCCM prevents shortcut collapse in consistency models for graph prediction by using contrastive negative pairs and input feature perturbation, leading to better performance than deterministic baselines.
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
iTARFlow augments normalizing flows with diffusion-style iterative denoising during sampling while preserving end-to-end likelihood training, reaching competitive results on ImageNet 64/128/256.
ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.
MASF redesigns the forward diffusion process to align with measurements, yielding a theoretically grounded likelihood score and up to 28.2x speedup on O(10^5)-dimensional Kolmogorov flow under sparse and nonlinear observation operators.
EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.
A conditioned diffusion model with SNR-weighted arbitrage penalty generates one-day-ahead arbitrage-free implied volatility surfaces and outperforms baselines on market data.
Improved consistency training techniques achieve FID scores of 2.51 on CIFAR-10 and 3.25 on ImageNet 64x64 in one sampling step, outperforming prior consistency training and distillation methods.
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
DiffUNet^2 is a bidirectional conditional diffusion model integrated with visual tools for probabilistic exploration of scientific time series across five evaluated datasets.
A domain-adapted diffusion model synthesizes heterogeneous PET images from uniform organ activity maps, achieving high quantitative accuracy (CCC > 0.92) and visual realism comparable to real scans.
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.
TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.
A temporal extension of TabDDPM generates coherent synthetic time-series sequences on the WISDM dataset that match real distributions and support downstream classification with macro F1 of 0.64.
Applies diffusion models to generate 10,000 neutrino mass matrices consistent with oscillation parameters in a seesaw model, revealing non-trivial distributions in CP phases and 0νββ effective mass.
Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.
OmniVLA-RL uses a mix-of-transformers architecture and flow-matching reformulated as SDE with group segmented policy optimization to surpass prior VLA models on LIBERO benchmarks.
citing papers explorer
-
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.