Sub-1-Bit LLM Compression via Latent Factorization

Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026) - SamsungLabs/LittleBit

70 points by brainless 14 days ago github.com 13 comments

Summary not yet generated for this article.

Loading more comments... ⌛

Scroll down to load more comments

No comments available.