3 papers
cs.MA2025
ASAP: an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training
Yuran Ding, Xinwei Chen, Xiaofan Zhang +1
Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing op…
cs.CR2025
SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories
Chihao Shen, Connor Dilgren, Purva Chiniya +3
This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++…
cs.CR2024
Constrained Decoding for Secure Code Generation
Yanjun Fu, Ethan Baker, Yu Ding +1
Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to en…