Qiang Tang receives funding from Google via Digital Future Initiative to support the research on this project. Moti Yung works for Google as a distinguished research scientist. Yanan Li is supported ...

Abstract: Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention.

Abstract: We define the fundamental practices and criteria for evaluating and using the Meta Llama 3 and OpenAI ChatGPT 3.5 and 4o large language models (LLMs) to translate parallel scientific Fortran ...

I produced a reverse-engineered .bmad manifest that documents what your installer created, enumerates individual ignore entries ("turds") rather than only parent directories, and includes mask entries ...

Data attribution in text-to-image generative models is a crucial yet underexplored problem, particularly at the regional level, where identifying the most influential training regions for generated ...