Thrilled to announce that I'll be joining UIUC CS @siebelschool as an Assistant Professor in Spring 2026!
📢 I’m looking for Fall '26 PhD students who are interested in the intersection of Software Engineering and AI, especially in LLM4Code and Code Agents. Please drop me an
Yiling Lou
113 posts
Joined June 2016
- Introducing our latest survey on LLM-based Agents for Software Engineering (SE) LLM-based agents have shown remarkable effectiveness in SE. This survey covers 106 papers and summarizes them from both SE and agent perspective. 📝arxiv.org/pdf/2409.02977 🧑💻github.com/FudanSELab/Age…
- LLM + Static Analysis ➡️ Static Bug Detection 🔥🔥🔥 Curious how LLM can enhance traditional static analysis in bug detection? Very excited to share our work INFERROI just accepted at ICSE 2025! @ICSEconf arxiv.org/pdf/2311.04448 [1/N]
- 🏆 Excited to share that our work "Recommending Analogical APIs via Knowledge Graph Embedding" received the ACM @sigsoft Distinguished Paper Award at @fseconf 2023! With Mingwei (@mliu918351), Yanjun, Xin (@XinPeng_Fudan), Zhong, Xueying (@dudulemon_dddd), and Tianyong!
- I’m chairing the session “Pre-trained and few-shot learning for SE”@ICSEconf . It’s starting now. Welcome to room 103
- Pls join us on April 20 at llm4code workshop co-located with icse24, if you are interested in llm for code! @LingmingZhang @devanbu Lintan @llm4codeVery excited to share the 1st @llm4code workshop has attracted 170+ registrations! If you’re at @ICSEconf and interested in LLMs, pls join us on April 20, we have 24 presentations and two keynotes on Code Llama (@b_roziere) and StarCoder2 (@LoubnaBenAllal1)! #icse24 #llm4code
- We are currently working on finalizing the benchmark and running more recent code models on ClassEval. Feel free to try ClassEval and help us improve this class-level code generation benchmark :)Great news! Our paper on evaluating LLMs for class-level code generation is accepted at ICSE @ICSEconf! Congrats to Xueying @dudulemon_dddd for leading! 🎉 Check our paper: [arxiv.org/pdf/2308.01861…] & ClassEval benchmark: [huggingface.co/datasets/Fudan…]. #ICSEAccepted #ClassEval #LLMs
- 🚨Just one week left to submit to #LLM4Code25!(Co-located with ICSE) We also offer a non-archival option, if selected, your camera-ready will be shared only on our workshop website, not the proceedings (no need to worry about double submission if you have other submission plan)📢Announcing the 2nd workshop on #LLM4Code, co-located with @ICSEconf 2025 in Ottawa, Canada 🇨🇦! 🎯We are calling for submissions: 🌟Website: llm4code.github.io 🌟Deadline: Nov 18, 2024 🌟8-page research paper / 4-page position paper (including references) 🚀Calling for
- 🚨 10 days left to submit to AIware 2025! 🏆🏆The best full-length papers will be recognized with an ACM SIGSOFT Distinguished Paper Awards📢 Call for Papers We invite submissions on the future of software in the FM era, including AI-powered development practices, LLMOps, trust, and SE education. 📄 Submission types: full papers, short papers, and literature reviews. 🔗 Full CFP: 2025.aiwareconf.org/track/aiware-2…
- Congratulations to all the authors! Looking forward to seeing you in Lisbon🎉 We just sent out the notifications for the first LLM4Code workshop! Congratulations to all authors of the 25 accepted papers! 🚀 Stay tuned at llm4code.github.io as we'll soon release the detailed paper list along with preprints! #LLM4Code2024 #ICSE24 @ICSEConf
- We are very happy to have @LoubnaBenAllal1 and @b_roziere for the keynotes on StarCoder2 and Code Llama. Please register for LLM4Code workshop at ICSE’24 @ICSEconf conf.researchr.org/program/icse-2… Join us on April 20th in Lisbon :)Introducing keynote speakers of #LLM4Code @ICSEconf! 🔊"Open development of Large Language Models for code with BigCode and StarCoder2" by @LoubnaBenAllal1 from @HuggingFace 🔊"Code Llama: Open Foundation Models for Code" by @b_roziere from @Meta Don't miss these great talks!
- Replying to @chengyuzh @lborouniversity and 2 othersCongratulations Chengyu!
- Replying to @yiling__LOUFor human-agent collaboration in SE tasks, we find that they mainly interact with each other during the planning, requirement, development or the evaluation phases.














