Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
Title resolution pending
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
By adding future visual state prediction and a dedicated inverse kinematics diffusion network that uses only visual boundary conditions, a 0.5B driving VLA recovers visual grounding and matches 7-8B models on NAVSIM-v2 and nuScenes.
Graph-based diffusion posterior sampling with added regularization for stable conductivity reconstructions in 2D electrical impedance tomography.
Equivariant SGMs achieve improved Wasserstein-1 generalization bounds on group-invariant distributions and learn the symmetrized score via equivariant vector fields without augmentation, with non-equivariant models incurring a quantifiable model-form error.
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
NoiseRater meta-learns instance-level importance scores for noise in diffusion training via bilevel optimization, then uses a two-stage pipeline to improve efficiency and generation quality on FFHQ and ImageNet.
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
DVG dynamically selects content-aware spatio-temporal acceleration strategies for diffusion-based video generation, delivering up to 7x speedup with near-lossless quality on models like HunyuanVideo.
Diffusion-APO synchronizes training noise with inference trajectories in video diffusion models to improve preference alignment and visual quality.
citing papers explorer
-
Generative Modeling with Flux Matching
Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
-
Grounding Driving VLA via Inverse Kinematics
By adding future visual state prediction and a dedicated inverse kinematics diffusion network that uses only visual boundary conditions, a 0.5B driving VLA recovers visual grounding and matches 7-8B models on NAVSIM-v2 and nuScenes.
-
Diffusion Graph Posterior Sampling for Nonlinear Inverse Problems with Application to Electrical Impedance Tomography
Graph-based diffusion posterior sampling with added regularization for stable conductivity reconstructions in 2D electrical impedance tomography.
-
Equivariant score-based generative models provably learn distributions with symmetries efficiently
Equivariant SGMs achieve improved Wasserstein-1 generalization bounds on group-invariant distributions and learn the symmetrized score via equivariant vector fields without augmentation, with non-equivariant models incurring a quantifiable model-form error.
-
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
-
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
NoiseRater meta-learns instance-level importance scores for noise in diffusion training via bilevel optimization, then uses a two-stage pipeline to improve efficiency and generation quality on FFHQ and ImageNet.
-
MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while improving structural consistency.
-
Dynamic Video Generation: Shaping Video Generation Across Time and Space
DVG dynamically selects content-aware spatio-temporal acceleration strategies for diffusion-based video generation, delivering up to 7x speedup with near-lossless quality on models like HunyuanVideo.
-
Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
Diffusion-APO synchronizes training noise with inference trajectories in video diffusion models to improve preference alignment and visual quality.