Learning a Flow to Self-Supervised Representations
cs.CV, cs.LG, stat.ML
Submitted: 2026-09-24
Updated: 2026-09-25
Comments: 33 pages, 2 figures, including appendix
Code: https://github.com/vincen-github/DM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Minimax Optimality of the Probability Flow ODE for Diffusion Models
- Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
- Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
- Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching
- A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
- DINOv3
- Adaptivity and Convergence of Probability Flow ODEs in Diffusion Generative Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models