AGMs use a lightweight learned potential V_phi with stop-gradient to selectively weight informative bridge samples in generative model training, yielding better fidelity and coverage.
Building normalizing flows with stochastic interpolants
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
-
Action-Inspired Generative Models
AGMs use a lightweight learned potential V_phi with stop-gradient to selectively weight informative bridge samples in generative model training, yielding better fidelity and coverage.
-
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.