Appears on
Articles3
StreamingVLM: Real-Time Vision-Language Model for Infinite Video Stream Processing
Insight
arxiv.org7mo ago
Efficient Training Data Reduction Using High-Fidelity Labels and Human Expertise
Insight
research.google9mo agoAnalyzing Loss Functions in Diffusion Bridge Samplers
Diffusion bridges in deep-learning methods for sampling from unnormalized distributions are analyzed, comparing the performance of Log Variance (LV) loss and reverse Kullback-Leibler (rKL) loss. The study shows that rKL loss with the log-derivative trick consistently outperforms LV loss, especially for diffusion bridges with learned diffusion coefficients.
Insight
arxiv.org11mo ago