Unverified50% confidenceFactExact time
Conditional flow matching (CFM) is a training objective under the flow matching framework that fits the instantaneous velocity of a path by constructing a continuous probability path from a source distribution to a target distribution (typically a straight-line interpolation path) and learning a time-dependent velocity field.
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFlow matching is a class of methods for training continuous-time generative models that learn a velocity field to transport a prior distribution along ODE trajectories to the data distribution, and at inference time a numerical integrator is used to solve iteratively, with the number of integration steps being the NFE.80% similarUnverifiedClassifier-Free Guidance (CFG) is one of the most mainstream guidance techniques in diffusion models and flow matching models, discarding conditions with a certain probability during training and, during sampling, subtracting the unconditional prediction from the conditional one via a formula and amplifying the guidance strength.75% similarUnverifiedLLMs are essentially pattern-matching systems based on statistical regularities, learning through pre-training on massive code corpora what code typically follows a given context.73% similarUnverifiedFlow Matching with Correction (FMC) is the training objective introduced by UniWALM, which teaches the model during training to recover from perturbed motion trajectories and adds no extra computational cost at inference time.72% similarVerifiedFlow matching is a generative model training method that directly learns a deterministic ODE path from the noise distribution to the data distribution, defines a linear interpolation path xt=(1-t)x₀+tx₁, and uses a neural network to learn to predict the velocity vector at every point along that path.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150318API
curl https://kongchang.com/api/v1/knowledge/claims/1150318MCP
get_claim(id=1150318)