1

Sub-1-Bit LLM Compression via Latent Factorization

github.com

SamsungLabs has released the official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026) for sub-1-bit LLM compression via latent factorization.

Sign in to suggest edits

Key sources

  1. DISCUSSIONbrainlessnews.ycombinator.com
Markdown