CodeMMR creates a unified embedding space for text, code, and images, outperforming baselines by 10 nDCG@10 points and boosting RAG code generation quality.
Magiclens: self- supervised image retrieval with open-ended instructions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval
CodeMMR creates a unified embedding space for text, code, and images, outperforming baselines by 10 nDCG@10 points and boosting RAG code generation quality.