In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships. Neighborhood-based dimensionality reduction (DR) methods can propagate this limitation by optimizing layouts from embedding-based neighborhoo...
Chang Won Kim, Jaewook Lee, Haeun Min et al.· 0 citations
Few-step generative models produce high-quality samples in one or a few evaluations. However, steering them toward desired properties remains difficult, especially when only black-box reward evaluations are available. While one could apply approaches developed for iterative diffusion and flow-based models, such as dire...
Woocheol Shin, Taeyoung Yun, Jiwon Sung et al.· 0 citations
This work introduces Few-step DPO (FestDPO), an extension of DPO for few-step generative models that leverages nonparametric likelihood estimation from empirical samples that makes sample-based approximation of DPO loss computationally feasible.
Jaewoo Lee, Kyuil Sim, Hyeongyu Kang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.