5 papers
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Yuntian Deng, Pengyu Nie, Stuart Shieber
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and…
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Wentao Zhang, Liliana Hotsko, Woojeong Kim +3
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…
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Liliana Hotsko, Yinxi Li, Yuntian Deng +1
Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG o…
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Yinxi Li, Yuntian Deng, Pengyu Nie
Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but drive…
Mix-of-Language-Experts Architecture for Multilingual Programming
Yifan Zong, Yuntian Deng, Pengyu Nie
Large language models (LLMs) have demonstrated impressive capabilities in aiding developers with tasks like code comprehension, generation, and translation. Supporting multilingual…