A new variational inference method uses neural networks to tilt Lévy measures, enabling scalable posterior inference for jump processes while preserving their discontinuous structure.
hub
Neural Stochastic Differ- ential Equations: Deep Latent Gaussian Models in the Diffu- sion Limit
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Introduces trajectory-law invariance to observation schedule as a continuity criterion for continuous-time causal PFNs, with a three-tier taxonomy and a random-DAG construction using fine-grid integration that outperforms naive integration in ablations.
A two-stage symbolic regression plus generative model framework recovers governing interaction terms and forcing in stochastic triad models while accurately predicting statistical moments up to order five.
DiffeoMorph learns distributed agent protocols to morph into complex 3D shapes from minimal initial conditions via equivariant GNNs and rotation-invariant Zernike loss.
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
Imagen Video generates high-definition text-conditional videos via a cascade of base and super-resolution diffusion models, achieving high fidelity and controllability.
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 diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance on video prediction and unconditional generation benchmarks.
Progressive distillation halves sampling steps repeatedly in diffusion models, reaching 4 steps with FID 3.0 on CIFAR-10 from 8192-step samplers.
Transformer components arise as the natural solution to precision-weighted directional state estimation on the hypersphere.
A variational method learns a neural approximation to the conditional backward-in-time score of the posterior SDE, inducing an ELBO for joint smoothing and parameter learning from sparse data.
NSP model fuses satellite and gauge data with neural processes and SDEs, outperforming 13 baselines and JAXA's operational product on a new 43k-sample US benchmark across six metrics.
MIOFlow 2.0 learns stochastic cellular trajectories from transcriptomics data via neural SDEs, unbalanced optimal transport for growth, and a joint latent space unifying gene expression with spatial features.
Stein Diffusion Guidance corrects approximate posteriors in diffusion sampling via a Stein variational mechanism and surrogate SOC objective to enable effective guidance beyond high-density regimes.
Neural mean-field games integrate mean-field game theory with neural SDEs to learn strategic interactions from data in a model-free way, demonstrated on games and viral dynamics.
An extension of the finite expression method using TranNet-initialized shallow neural operators is proposed as an effective solver for high-dimensional partial differential equations.
citing papers explorer
-
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.