'CodeImprove: Program Adaptation for Deep Code Models' was published in the Proceedings of the IEEE/ACM 47th International Conference on Software Engineering on 27 April 2025, spanning pages 514–526.
Sources
More in Technology
- Researchers at the University of Texas at Austin developed an AI-based semantic decoder that translates brain activity into a continuous stream of text using functional MRI scans, without requiring a surgical implant.
- Researchers used artificial intelligence and X-ray scans to decipher parts of a 2,000-year-old papyrus scroll burned in the A.D. 79 eruption of Mount Vesuvius.
- FrontierMath is a math benchmark whose difficult questions remain unpublished so that AI companies cannot train their models against them.
- Llama3-RankRAG significantly outperformed Llama3-ChatQA-1.5 and GPT-4 models on nine knowledge-intensive benchmarks.
- Agreement between AI models and physician majority vote on NEJM Image Challenge cases was low, with Cohen's kappa of 0.08 for both GPT-4o and Claude 3.7, and 0.24 for Doubao.
- Researchers from Denmark built a search engine dedicated to rare diseases called FindZebra.