Program-as-Weights: A Programming Paradigm for Fuzzy Functions
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%mirkofr/FERNme →
- PossiblePossibly related (embedding) · 46%NeuralInverse/neuralinverse →
- PossiblePossibly related (embedding) · 46%langfuse/langfuse →
- PossiblePossibly related (embedding) · 46%potpie-ai/potpie →
- LinkedLinked via arxiv author · 85%Wentao Zhang →
“Program-as-Weights: A Programming Paradigm for Fuzzy Functions”
- LinkedLinked via arxiv author · 85%Liliana Hotsko →
“Program-as-Weights: A Programming Paradigm for Fuzzy Functions”
- LinkedLinked via arxiv author · 85%Woojeong Kim →
“Program-as-Weights: A Programming Paradigm for Fuzzy Functions”
- LinkedLinked via arxiv author · 85%Pengyu Nie →
“Program-as-Weights: A Programming Paradigm for Fuzzy Functions”