Token-Oriented Preference Optimization (ToPO) is proposed, which builds a token-conditioned spatial-temporal weighting map for each pair of Diffusion-DPO, and achieves state-of-the-art performance among the compared methods with only 500 training updates.
Jun-Tao Xu, Shi-Hong Li, Ho-Yin Au et al.· 1 citation
DART is proposed, a training-free reparameterization method that transports source LoRAs into aligned coordinates through a low-rank distillation bridge and complements response calibration, with adapter-level benefits encompassing both functional preservation and reduced negative transfer.
Shi-Hong Li, Jun-Tao Xu, Cao Jin et al.· 1 citation
ToPO (Token-Oriented Preference Optimization) constructs a per-minibatch, detached, separable spatial-temporal route from branchwise squared-residual contrast in a frozen reference denoiser for attention-based, noise-prediction latent diffusion.
Jun-Tao Xu, Shi-Hong Li, Ho-Yin Au et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.