🚀Can LLMs repair programs without known buggy hunks?🤔 💡 My student Junjielong Xu's #ICSE2025 paper reveals that current infilling approaches constrain LLMs' repair potential. By simply aligning the task objective from fixing buggy hunks to rewriting the entire program with tests,

Truly humbled and honored to receive the IEEE CS TCSE Rising Star Award. Thanks a lot for the help along the way from my supervisors, referees, students, and co-authors. Will continue to focus on impactful projects about AI4SE and SE4AI. 🎯 tc.computer.org/tcse/awards/

📢 Can LLMs locate software service failures? 🤔 My student Junjielong Xu's #ICLR2025 paper introduces OpenRCA, the first benchmark dataset for evaluating LLMs' root cause analysis capabilities in software systems. LLMs/Agents need to analyze system telemetry data to infer results

Our paper "Top Score on the Wrong Exam" paper will be presented at #ISSTA25 🐣 in Trondheim! 📝mpi-softsec.github.io/papers/ISSTA25… 🧑‍💻github.com/niklasrisse/To… // Niklas Risse Jing Liu (fuzzing.bsky.social).

Recently we have four papers accepted to #ACL2025 and two papers accepted to #ICML2025! It is with great pleasure and excitement that all my papers during PhD study have been accepted! And I finally got first-author papers in all three ML conferences (NeurIPS, ICLR, and ICML)!

Trust your AI, but can it trust itself? 🤔 Introducing an online reinforcement learning framework, RISE (Reinforcing Reasoning with Self-Verification), enabling LLMs to simultaneously level-up BOTH their problem-solving AND self-checking skills! 🧐 Problems tackled: ✅