New LLM Compression: Under 1 Bit Per Param
andrewgwils · x · 2026-07-15
This repost highlights a research preview on LLM compression: the author introduces requential coding, claiming it can achieve compression of less than 1 bit per parameter.
The post also emphasizes that this work attempts to explain a broader question: why scaling up model size won't hit a "generalization wall". The original tweet includes links to the paper and co-author details.
Related event: New Research Compresses LLMs to Sub-1-Bit Per Parameter(3 posts)→
More from Research
- DeepMind paper: LLMs can't sample randomly on their own, only convert given seeds — rohanpaul_ai · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- Mathathon 2.0 launches with Terence Tao's SAIR, $1.5M in compute for teams — _sathvikr · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27