Episode
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
- Podcast
- Daily Paper Cast
- Published
- Jul 4, 2026
- Duration seconds
- 1466
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/196c54b8
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/program-as-weights-a-programming-paradigm-for-fuzzy-functions/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/program-as-weights-a-programming-paradigm-for-fuzzy-functions.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 58 | cs.LG, cs.AI, cs.CL Authors: Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng Title: Program-as-Weights: A Programming Paradigm for Fuzzy Functions Arxiv: http://arxiv.org/abs/2607.02512v1 Abstract: Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.