News

2026

We are hosting CRC@CSAW 2026

less than 1 minute read

Published: September 16, 2026

We are hosting the inaugural Cyber Reasoning Challenge at CSAW (CRC@CSAW 2026), a student competition on autonomous vulnerability discovery and repair. Teams build cyber reasoning systems that find vulnerabilities in real software, demonstrate them with a proof of vulnerability, and generate patches that fix the bugs while preserving program functionality. See the official CSAW event page for registration and competition details, and the CRC@CSAW GitHub repository for technical resources and updates.

NYU Tandon launches NSOC

less than 1 minute read

Published: August 24, 2026

NYU Tandon has launched the NYU Software Supply Chain Security Operations Center (NSOC), an NYU Center for Cybersecurity initiative that embeds master’s students in open-source communities for a year of hands-on supply-chain security work. Prof. Jiahao Yu co-founded NSOC with Justin Cappos, Andrew Nesbitt, and Vlad-Stefan Harbuz. The first cohort starts in January 2027. More at nsoc.engineering.nyu.edu.

Jiahao Yu joins NYU Abu Dhabi

less than 1 minute read

Published: June 04, 2026

Jiahao Yu has joined the Department of Computer Engineering at New York University Abu Dhabi as a Tenure-Track Assistant Professor and Principal Investigator of the Secure Reasoning Lab. The lab is actively looking for self-motivated Ph.D. students and postdocs. See Join Us.

2025

PatchAgent selected as a CSAW 2025 finalist

less than 1 minute read

Published: October 06, 2025

Our work PatchAgent was accepted as a CSAW 2025 finalist (Technical Impact Runner-up). We presented the work in New York City.

GPO covered by MIT Technology Review China

less than 1 minute read

Published: October 05, 2025

Our work GPO: Learning from Critical Steps to Improve LLM Reasoning was covered by MIT Technology Review China.

EntroPO ranks 1st on SWE-bench Lite (open-weight)

less than 1 minute read

Published: October 05, 2025

The official SWE-bench Verified and SWE-bench Lite open-weight leaderboards were updated. EntroPO ranks 1st on SWE-bench Lite and 5th on SWE-bench Verified, behind only models about 10× larger.