BS in Computer Science · Minors in Mathematics & Physics · Honors Student University of North Carolina at Pembroke
Hi 👋! I work at the intersection of AI safety & alignment and natural language processing. Read my latest work, DPBench: Large Language Models Struggle with Simultaneous Coordination. I'm advised by Dr. Prashanth BusiReddyGari, previously worked with Dr. Shaohu Zhang, and am currently an AI Safety Research Fellow at Algoverse.
My current work uses reinforcement learning (GRPO, QLoRA) to train LLMs as agents on classical concurrency problems like Dining Philosophers.
I also founded and run UNC Pembroke's AI student organization, AI@UNCP, and have organized HackUNCP 2025 and HackUNCP 2026.
N. Hasan and P. BusiReddyGari, "Benchmarking Large Language Models for Zero-shot and Few-shot Phishing URL Detection," in Proc. LAW Workshop, 39th Conference on Neural Information Processing Systems (NeurIPS), 2025. [Paper] [arXiv]
N. Hasan and P. BusiReddyGari, "Time-Complexity Characterization of the NIST Lightweight Cryptography Finalists," in Proc. IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, 2026, pp. 1193-1196. [DOI] [arXiv]
N. Hasan and P. BusiReddyGari, "DPBench: Large Language Models Struggle with Simultaneous Coordination," arXiv preprint arXiv:2602.13255, Feb. 2026. [arXiv] [Code]
N. Hasan, P. BusiReddyGari, H. Zhao, Y. Ren, J. Xu, and S. Zhang, "Phishing Email Detection Using Large Language Models," arXiv preprint arXiv:2512.10104, Dec. 2025. [arXiv]
| Project | Description |
|---|---|
| DPBench | Benchmark for LLM multi-agent coordination using Dining Philosophers |
| SplitComp | Modeling when labs comply, evade, or split compute across jurisdictions |
| SAGE | Synchronized Agents for Generalized Expertise, a multi-agent research, debate and synthesis framework |
| Sift | Reads raw IT tickets and returns structured resolution paths |
I'm always happy to discuss research ideas or potential collaborations. Feel free to reach out.