Sublime

Vector databases for AI memory just got replaced by MP4 files. Store millions of text chunks in MP4 files instead of expensive vector databases with lightning-fast semantic search. No database needed. 100% Opensource. https://t.co/iuIS5ElHsM

a technique i'm increasingly believing is going to be really useful in large-scale synth data pipelines is the use of graph algorithms to do semantic deduplication submitted a paper about this a while back, never got around to cleaning it up for arxiv, but it's a neat trick https://t.co/XNVRTWxCSq

The results in this paper look good. I want to believe. https://t.co/Vg3ing9t0g https://t.co/HaECdszUE6

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces abs: https://t.co/iX3hg5HOVn github: https://t.co/TPwZNSJgaD t2i model requiring less than 10 steps to sample high-fidelity images https://t.co/veHSlEmkaG

Introducing MaPO, a memory-efficient technique for aligning T2I diffusion models on preference data 🔥 We eliminate the need to have a reference model when performing alignment fine-tuning. Code, models, datasets, and paper are up... See more