Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
citing papers explorer
-
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.