An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications , year=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
years
2026 12representative citing papers
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
Energy-based model with covariance regularization computes normalized posteriors for linear inverse problems without retraining, enabling adaptive sampling and blind estimation on image datasets.
A compositional diffusion world model integrates three specialized memory experts via contrastive product-of-experts to improve temporal consistency, past recall, and navigation while scaling to long contexts without quadratic costs.
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
GRAB improves multi-table QA performance by encoding relational data as graphs and bridging structural signals to frozen LLMs through latent tokens.
Near-reversible Runge-Kutta ODE solvers combined with vector-field smoothing deliver more stable and higher-fidelity text-guided edits in diffusion models than exactly reversible schemes.
RNA-FM is a flow-matching generative model that predicts genome-wide bulk RNA-seq expression from WSIs by learning a conditional velocity field, outperforming deterministic baselines.
citing papers explorer
-
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
-
Let EEG Models Learn EEG
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
-
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
-
Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
-
Learning Normalized Energy Models for Linear Inverse Problems
Energy-based model with covariance regularization computes normalized posteriors for linear inverse problems without retraining, enabling adaptive sampling and blind estimation on image datasets.
-
Composition of Memory Experts for Diffusion World Models
A compositional diffusion world model integrates three specialized memory experts via contrastive product-of-experts to improve temporal consistency, past recall, and navigation while scaling to long contexts without quadratic costs.
-
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
-
Latent Bridges for Multi-Table Question Answering
GRAB improves multi-table QA performance by encoding relational data as graphs and bridging structural signals to frozen LLMs through latent tokens.
-
Stable and Near-Reversible Diffusion ODE Solvers for Image Editing
Near-reversible Runge-Kutta ODE solvers combined with vector-field smoothing deliver more stable and higher-fidelity text-guided edits in diffusion models than exactly reversible schemes.
-
RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction
RNA-FM is a flow-matching generative model that predicts genome-wide bulk RNA-seq expression from WSIs by learning a conditional velocity field, outperforming deterministic baselines.