Program-as-Weights: Compiling English Functions into Local Neural Programs
yuntiandeng · x · 2026-07-04
HuggingPapers shared the paper "Program-as-Weights," which introduces a method to describe a function in English and then "compile" it into a locally executable neural program. Built on a model with around 0.6B parameters that emphasizes interpretability, this approach explores a novel paradigm for representing programs as neural network weights.
More from Research
- Open-source decision models sold their own base in Red Alert 2 — then learned until no human could beat them — heathercmiller · 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