DCFM is a new decentralized framework that enforces structural constraints on generative factors across siloed data sources to produce novel compositions via peer interactions.
hub
Guided flows for generative modeling and decision making
26 Pith papers cite this work. Polarity classification is still indexing.
26
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DivIn samples initial noise from a guidance potential posterior via Langevin dynamics to improve diversity in class-to-image and text-to-image generation.
StAD distills divergence of PF-ODEs via the Langevin-Stein operator for faster, lower-variance likelihood estimation in generative models without Jacobian costs.
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
TouchGuide improves contact-rich robot manipulation by steering diffusion or flow-matching visuomotor policies with tactile feasibility scores from a contrastively trained Contact Physical Model.
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
DRFS is a new inversion-free editing technique for rectified flow models that models source-target velocity discrepancies and applies a time-dependent shift to improve fidelity and unify prior methods like DDS and FlowEdit.
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
Adapts Flow Matching from generative AI to probabilistic inversion, evaluated on a simple 2D velocity model and the OpenFWI seismic dataset.
MICE modifies joint attention biases in Multimodal Diffusion Transformers to enable concurrent multi-instance edits while reducing semantic interference via user masks.
Reversal Q-Learning (RQL) proposes reversing flows for virtual trajectories and bias-variance reduction in an expanded MDP to train flow policies, reporting best average performance on 50 simulated robotic tasks versus prior flow-based offline RL methods.
MoMa QL uses MMD moment matching to enforce distribution-level convergence of conditional score functions in flow-based RL policies for improved sampling efficiency.
FA-OPD co-trains a flow-matching teacher and MLP student via adversarial dual on-policy distillation, improving robustness over baselines on six robot benchmarks with noisy or limited demonstrations.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
VicoEdit performs training-free image editing by transforming source images directly with visual context and concept-alignment-guided posterior sampling, outperforming training-based methods.
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
VQActFlow discretizes action chunks via vector quantization, generates code sequences with variational flow matching, and applies inference-time guidance to steer multi-task robot policies toward instructed and feasible modes.
FluxFlow uses conservative pixel-space flow-matching with uncertainty weights and Wiener test-time correction to outperform baselines on photometric and scientific accuracy for ground-to-space super-resolution, validated on a new real 19,500-pair DESI-HST dataset.
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
PolyFlow is a constrained flow matching framework that embeds polytope constraints into the model dynamics for zero-violation generation with reduced inference latency in planning and control tasks.
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalization from sparse data.
citing papers explorer
-
Compositional Generative Modeling from Decentralized Data
DCFM is a new decentralized framework that enforces structural constraints on generative factors across siloed data sources to produce novel compositions via peer interactions.
-
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
-
Probabilistic Inversion with Flow Matching
Adapts Flow Matching from generative AI to probabilistic inversion, evaluated on a simple 2D velocity model and the OpenFWI seismic dataset.
-
Reversal Q-Learning
Reversal Q-Learning (RQL) proposes reversing flows for virtual trajectories and bias-variance reduction in an expanded MDP to train flow policies, reporting best average performance on 50 simulated robotic tasks versus prior flow-based offline RL methods.
-
Moment Matching Q-Learning
MoMa QL uses MMD moment matching to enforce distribution-level convergence of conditional score functions in flow-based RL policies for improved sampling efficiency.
-
Adversarial Dual On-Policy Distillation from Expressive Teacher
FA-OPD co-trains a flow-matching teacher and MLP student via adversarial dual on-policy distillation, improving robustness over baselines on six robot benchmarks with noisy or limited demonstrations.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
-
Latent Stochastic Interpolants
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
-
Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
-
PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update
PolyFlow is a constrained flow matching framework that embeds polytope constraints into the model dynamics for zero-violation generation with reduced inference latency in planning and control tasks.
-
Flow Matching Guide and Code
Flow Matching is a generative modeling framework with mathematical foundations, design choices, extensions, and open-source PyTorch code for applications like image and text generation.