Bo Wu
2 papers · Latest:
Cryptography & Security
How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
Code representation significantly impacts false positives in cross-language LLM vulnerability detection, with text fine-tuning increasing FPR due to surface-cue memorization.
2604.27714
Artificial IntelligenceThe Llama 3 Herd of Models
Llama 3 is a new family of large multilingual foundation models excelling in language, coding, reasoning, and multimodal tasks, rivaling GPT-4 in quality and offering extensive public releases.
2407.21783
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.