AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
Align your flow: Scaling continuous- time flow map distillation
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
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.
OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
Drift Flow Matching connects direct transport maps from Drift Models with flow-based iterative refinement to enable adaptive computation in generative modeling.
citing papers explorer
-
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.