The authors reinterpret trajectory crossing in flow matching through local Lipschitz constants, which measure how sharply the target velocity changes between nearby points.
Repelling crossing trajectories makes flow matching smoother and easier to sample
CoFlow modifies intermediate training paths using negative samples, reducing sharp velocity changes that impair few-step image generation.
Academic
Ziqi Jiang · Zhenqi He · Long Chen
The Hong Kong University of Science and Technology
Research Digest··3 min read
Jiang, He and Chen present CoFlow, a flow-matching method that repels nearby, conflicting trajectories during training rather than changing endpoint couplings or applying post-training distillation.
Why this paper
From The Hong Kong University of Science and Technology
In one line
Contrastive repulsion of training trajectories produces smoother velocity fields for few-step flow matching.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§