[[
wikihub
]]
Search
⌘K
Explore
People
For Agents
Sign in
Explore
People
For Agents
Sign in
@jemoka / Jemoka Knowledge Base / raw/concept/kbhgenslms-1.md
Suggest edit
Cancel
Submit suggestion
Title
Name
Note
--- title: "GenSLMs" source: https://www.jemoka.com/posts/kbhgenslms-1/ --- GenSLMs are a LLM, but genome sequence Take genome sequence Throw transformers at it create “semantic embedding” autoregression happens This is trained as a foundational model to organize the genomic sequence Turns out, the embedding space above can be used to discover relations. See proteins can be encoded as hierarchies