arXiv Machine Learning
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 2
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.
arXiv AI
1d ago
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
The paper introduces a new method for training data attribution in diffusion models called TID, which uses a local score discrepancy measure and can be estimated without retraining. It further distills this approach into TIDE, a forward‑only student that reproduces the teacher’s rankings using internal activations, achieving comparable accuracy at dramatically lower query cost. Experiments on CIFAR‑10, ArtBench‑10, and MS‑COCO show that TID outperforms existing methods and TIDE attributes samples in milliseconds, faster than generation itself.
arXiv Machine Learning
Jun 2
Exploring and Exploiting Stability in Latent Flow Matching
arXiv:2605. 08398v2 Announce Type: replace Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage.
arXiv AI
Jul 7
Score-Regularized Joint Sampling with Importance Weights for Flow Matching
arXiv:2511. 17812v3 Announce Type: replace-cross Abstract: Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets.
arXiv Machine Learning
Jun 2
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
arXiv:2605. 00941v4 Announce Type: replace Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem.
arXiv AI
Sep 2
Training-Free Refinement of Flow Matching with Divergence-based Sampling
The paper introduces Flow Divergence Sampler (FDS), a training‑free method that refines intermediate states in flow‑matching models by using the divergence of the marginal velocity field to detect and correct misguidance toward low‑density regions. FDS operates during inference, requires no additional training, and can be applied as a plug‑and‑play module with standard solvers and existing flow backbones. Experiments show that FDS consistently improves fidelity in tasks such as text‑to‑image synthesis and inverse problems.