Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
super hub Mixed citations
Denoising Diffusion Probabilistic Models
Mixed citation behavior. Most common role is background (55%).
155
Pith papers citing it
Background
55% of classified citations
abstract
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at https://github.com/hojonathanho/diffusion
hub tools
citation-role summary
background 18
method 9
baseline 3
other 1
citation-polarity summary
claims ledger
- abstract We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score
authors
co-cited works
representative citing papers
MF-PID turns independent diffusion samples into mean-field interacting agents, proving that quadratic interactions yield exact linear mean interpolation and delivering 19-24% energy savings in demand-response control.
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
DDIMs construct non-Markovian diffusion processes that share DDPM training objectives but allow much faster reverse sampling, demonstrated empirically at 10-50x wall-clock speedup.
DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.
Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
Nested-GPT is an autoregressive Transformer surrogate that generates variable-multiplicity parton showers while enforcing ordered Markovian branching and matches reference Monte Carlo results for leading-log non-global logarithm resummation in the large-Nc limit.
Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
Creativity is defined as meta-learning where a frozen diffusion creator optimizes candidates for rapid improvement by an adapting appraiser such as an autoencoder or CLIP adapter.
DSSP is a history-conditioned diffusion state space policy that uses SSMs to encode full observation streams with an auxiliary dynamics objective and hierarchical fusion, achieving SOTA results with reduced model size in robot manipulation.
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
LVO applies optimization-based feature visualization to latent diffusion models after disentangling their representations with sparse autoencoders, yielding recognizable concept images on a fine-tuned Stable Diffusion model that are clearer than those from entangled baselines.
Tempered Guided Diffusion uses annealed SMC to produce consistent particle approximations to the posterior for training-free conditional diffusion sampling, outperforming independent guided trajectories in experiments.
Action Agent pairs LLM-driven video generation with a flow-constrained diffusion transformer to produce velocity commands, raising video success to 86% and delivering 64.7% real-world navigation on a Unitree G1 humanoid.
Influpaint uses generative diffusion models on image-encoded influenza data to produce realistic and diverse epidemic trajectories that match leading ensemble methods in accuracy.
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
A diffusion generative inverse model conditioned on temperature targets produces diverse, physically plausible urban vegetation patterns that achieve specified regional temperature shifts.
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.
ExpertEdit edits novice motions to expert skill levels by learning a motion prior from unpaired videos and infilling masked skill-critical spans.
MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.
Anchored Cyclic Generation uses anchor features from known music to mitigate error accumulation in autoregressive models, with the Hi-ACG framework delivering better long-sequence symbolic music and music completion performance.
Full-sequence masking in SFT unlocks prompt infilling for masked diffusion language models, producing templates that match or surpass hand-designed ones and transfer across models.
citing papers explorer
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
Normalizing Flows with Iterative Denoising
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.
-
LTX-Video: Realtime Video Latent Diffusion
LTX-Video integrates Video-VAE and transformer for 1:192 latent compression and real-time video diffusion by moving patchifying to the VAE and letting the decoder finish denoising in pixel space.