5 papers
Characterizing the Quality Profile of AI-Generated C++ in Production
Michael Tran, Fred Lewis, Kun Yang +5
The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off, revealing persistent challeng…
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Suryash Yagnik, Shubham Gaur, Saksham Thakur +3
Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of CounterFact, 0.6% of ZSRE, and le…
Customizing an LLM for Enterprise Software Engineering
Aditya Kini, Satish Chandra, Milad Hashemi +15
Enterprise software development is a continuous evolutionary process, characterized by incremental additions, architectural revisions, production deployments and rigorous maintenan…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Understanding and supporting how developers prompt for LLM-powered code editing in practice
Daye Nam, Ahmed Omran, Ambar Murillo +6
Large Language Models (LLMs) are rapidly transforming software engineering, with coding assistants embedded in an IDE becoming increasingly prevalent. While research has focused on…