Markov chain Phase-Type decoders in VAEs overcome the structural inability of Gaussian-Lipschitz models to produce heavy-tailed outputs, cutting tail KS distance by up to 6x and extreme quantile error by up to 10x on synthetic Pareto data.
Tutorial on variational autoencoders,
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
TacticGen generates realistic, adaptable football tactics via a multi-agent diffusion transformer trained on 3.3M events and 100M frames, supporting rule-, language-, or model-based guidance at inference time.
A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data statistics with approximately six orders of magnitude computational speedup.
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
SEGP-VAE learns stable low-dimensional LTI systems from video data by deriving GP mean and covariance from LTI equations and using a complete unconstrained parametrization of semi-contracting systems.
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
LEGO selects CVAE training targets from bottleneck regions on near-optimal paths and ensures diversity across regions, with formal definitions and performance guarantees.
Dim-R2 extends R2 to arbitrary dimensions, supplies multidimensional accuracy views, and reduces noise sensitivity for better regression evaluation.
A CVAE-based approach learns distributions over responsibility allocations in multi-agent scenes by grounding them in induced controls through differentiable optimization, showing strong prediction on driving data.
Variational autoencoders generate jerk signals from torque inputs in electric drivetrains and outperform physics-based baselines without detailed parametrization.
Auto-encoder approximates SEOBNRv4 waveforms for four-parameter aligned-spin binaries, delivering 4 orders of magnitude speedup at median mismatch of 10^{-2}.
WriterForcing combines keyphrase attention and non-generic word promotion in Seq2Seq models to produce more diverse and interesting story endings.
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.
A route-specific deep generative model learns the probability distribution of bus trip ETAs from historical data alone and conditions updates on real-time trip progress.
Extends Social-STGCNN with CVAE for multimodal trajectory prediction and reports moderate gains plus better diversity on ETH/UCY benchmarks and robot data.
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
A structured survey of audio bandwidth extension that organizes the transition from deterministic discriminative DNNs to generative approaches including GANs, diffusion models, and flow-based methods.
citing papers explorer
-
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
Markov chain Phase-Type decoders in VAEs overcome the structural inability of Gaussian-Lipschitz models to produce heavy-tailed outputs, cutting tail KS distance by up to 6x and extreme quantile error by up to 10x on synthetic Pareto data.
-
TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
TacticGen generates realistic, adaptable football tactics via a multi-agent diffusion transformer trained on 3.3M events and 100M frames, supporting rule-, language-, or model-based guidance at inference time.
-
A flow-matching generative model for event-by-event jet-induced hydro response in high-energy heavy-ion collisions
A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data statistics with approximately six orders of magnitude computational speedup.
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
-
Stability Enhanced Gaussian Process Variational Autoencoders
SEGP-VAE learns stable low-dimensional LTI systems from video data by deriving GP mean and covariance from LTI equations and using a complete unconstrained parametrization of semi-contracting systems.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning
LEGO selects CVAE training targets from bottleneck regions on near-optimal paths and ensures diversity across regions, with formal definitions and performance guarantees.
-
A dimensional R2 regression metric
Dim-R2 extends R2 to arbitrary dimensions, supplies multidimensional accuracy views, and reduces noise sensitivity for better regression evaluation.
-
Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions
A CVAE-based approach learns distributions over responsibility allocations in multi-agent scenes by grounding them in induced controls through differentiable optimization, showing strong prediction on driving data.
-
Drivetrain simulation using variational autoencoders
Variational autoencoders generate jerk signals from torque inputs in electric drivetrains and outperform physics-based baselines without detailed parametrization.
-
Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
Auto-encoder approximates SEOBNRv4 waveforms for four-parameter aligned-spin binaries, delivering 4 orders of magnitude speedup at median mismatch of 10^{-2}.
-
WriterForcing: Generating more interesting story endings
WriterForcing combines keyphrase attention and non-generic word promotion in Seq2Seq models to produce more diverse and interesting story endings.
-
Neural Embedding for Physical Manipulations
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.
-
To each route its own ETA: A generative modeling framework for ETA prediction
A route-specific deep generative model learns the probability distribution of bus trip ETAs from historical data alone and conditions updates on real-time trip progress.
-
On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
Extends Social-STGCNN with CVAE for multimodal trajectory prediction and reports moderate gains plus better diversity on ETH/UCY benchmarks and robot data.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
-
A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models
A structured survey of audio bandwidth extension that organizes the transition from deterministic discriminative DNNs to generative approaches including GANs, diffusion models, and flow-based methods.