2 papers
cs.SE2026
SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation
Weifeng Sun, Ye Fan, Yuchen Chen +6
Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limit…
cs.SE2026
UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning
Ye Fan, Jidong Ge, Chuanyi Li +2
While pre-trained models have achieved remarkable success in code search, their multilingual capabilities remain a major hurdle, plagued by data imbalance, cross-lingual semantic i…