Indraneil Paul
2 papers · Latest:
Software Engineering
Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring
Themis introduces multilingual, multi-criteria code reward models trained on a new large preference dataset to improve code generation beyond functional correctness.
2605.00754
Software EngineeringStarCoder 2 and The Stack v2: The Next Generation
StarCoder2 is a next-generation open-source Code LLM trained on a vastly expanded and diverse dataset, achieving state-of-the-art performance on multiple code benchmarks while being more parameter-efficient than larger models.
2402.19173
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.