Strong Stochastic Flow Maps learn the strong solution map of additive-noise SDEs via a pathwise-convergent polynomial Brownian approximation, generalizing deterministic flow maps and enabling simulation-free training that outperforms prior weak-convergence stochastic methods on image generation and
hub
How to build a consistency model: Learning flow maps via self-distillation
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 14representative citing papers
A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
NTM models each generative reverse step as a conditional normalizing flow with a hybrid shallow-deep architecture, enabling exact-likelihood training and strong four-step sampling performance on text-to-image tasks.
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
IMPFM is a multi-particle flow-map sampling method with sequential posterior sharing and interaction-aware correction that targets a KL-tilted distribution for global exploration in online feedback search.
SCALLOP replaces Hutchinson's trace estimator with a scalable, vectorized likelihood distillation objective for F2D2 flow maps, cutting training variance and time while improving performance on molecular Boltzmann generators and image data.
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank them below trained models.
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
FlashMol produces chemically valid 3D molecules in 4 steps via distribution matching distillation with respaced timesteps and Jensen-Shannon regularization, matching or exceeding 1000-step teacher performance on QM9 and GEOM-DRUG.
Continuous flows on token embeddings with flow-map distillation produce one-step language models whose quality exceeds recent 8-step discrete diffusion baselines on LM1B and OpenWebText.
A product-kernel interpolation method is proposed that augments state with parameters to produce symplectic large-step predictors for Hamiltonian dynamics by construction, with error bounds that extend from the non-parameterized case.
citing papers explorer
-
Strong Stochastic Flow Maps
Strong Stochastic Flow Maps learn the strong solution map of additive-noise SDEs via a pathwise-convergent polynomial Brownian approximation, generalizing deterministic flow maps and enabling simulation-free training that outperforms prior weak-convergence stochastic methods on image generation and
-
Multiplayer Interactive World Models with Representation Autoencoders
A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
-
Generative Pseudo-Force Fields for Molecular Generation
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
-
Aligning Flow Map Policies with Optimal Q-Guidance
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
-
Normalizing Trajectory Models
NTM models each generative reverse step as a conditional normalizing flow with a hybrid shallow-deep architecture, enabling exact-likelihood training and strong four-step sampling performance on text-to-image tasks.
-
Generative Modeling of Discrete Data Using Geometric Latent Subspaces
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
-
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
IMPFM is a multi-particle flow-map sampling method with sequential posterior sharing and interaction-aware correction that targets a KL-tilted distribution for global exploration in online feedback search.
-
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
SCALLOP replaces Hutchinson's trace estimator with a scalable, vectorized likelihood distillation objective for F2D2 flow maps, cutting training variance and time while improving performance on molecular Boltzmann generators and image data.
-
KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
-
Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics
Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank them below trained models.
-
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
-
FlashMol: High-Quality Molecule Generation in as Few as Four Steps
FlashMol produces chemically valid 3D molecules in 4 steps via distribution matching distillation with respaced timesteps and Jensen-Shannon regularization, matching or exceeding 1000-step teacher performance on QM9 and GEOM-DRUG.
-
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
Continuous flows on token embeddings with flow-map distillation produce one-step language models whose quality exceeds recent 8-step discrete diffusion baselines on LM1B and OpenWebText.
-
Symplecticity-preserving prediction of parameter-dependent Hamiltonian dynamics by Generalized Kernel Interpolation
A product-kernel interpolation method is proposed that augments state with parameters to produce symplectic large-step predictors for Hamiltonian dynamics by construction, with error bounds that extend from the non-parameterized case.