Kexin Pei
@Kexin_Pei
Followers
1K
Following
2K
Media
0
Statuses
199
Assistant Prof @UChicago 2024. CS Ph.D. @Columbia. Ex @GoogleDeepMind @MSFTResearch @Purdue. Security, SE, and ML. AISec+ML4Code.
New York, USA
Joined April 2017
⏰ 3 days left to submit to #LLM4Code2026 (co-located with @ICSEconf 2026)! Pls submit by Oct 31: https://t.co/TdfOMMXw7V We hope to create a platform for researchers/practitioners to discuss the latest in LLMs/Agents for Code across diverse fields: SE, PL, ML, and beyond.
llm4code.github.io
ICSE 2026 Workshop on Large Language Model for Code
Excited to announce the 3rd LLM4Code workshop collocated with ICSE26 @ICSEconf in Rio, Brazil🇧🇷! 🌟Website: https://t.co/vD4NQSmKcl 🌟Deadline: Oct 31 🌟8-page research paper/4-page position paper (including references) @LingmingZhang @yiling__LOU @devanbu @Kexin_Pei @llm4code
0
6
12
Thrilled to share that I received the ACM SIGOPS Mark Weiser Award at SOSP 2025! All (read: ALL) the research it recognizes was joint with amazing students, postdocs, and collaborators — I’m just the lucky representative. Grateful to all who made it possible ♥️
4
3
71
Excited to announce the 3rd LLM4Code workshop collocated with ICSE26 @ICSEconf in Rio, Brazil🇧🇷! 🌟Website: https://t.co/vD4NQSmKcl 🌟Deadline: Oct 31 🌟8-page research paper/4-page position paper (including references) @LingmingZhang @yiling__LOU @devanbu @Kexin_Pei @llm4code
llm4code.github.io
ICSE 2026 Workshop on Large Language Model for Code
0
7
26
🚀The submission ddl has been extended to Friday, 31 Oct 2025! Look forward to your high-quality submission!
Announcing the 3rd workshop on #LLM4Code, co-located with @ICSEConf 2026 in Rio de Janeiro, Brazil 🇧🇷! 🎯We are calling for submissions: 🌟Website: https://t.co/Ai3nseQVKP 🌟Deadline: Oct 20, 2025 🌟8-page research paper / 4-page position paper (including references)
0
3
6
Announcing the 3rd workshop on #LLM4Code, co-located with @ICSEconf 2026 in Rio de Janeiro, Brazil 🇧🇷! 🎯We are calling for submissions: 🌟Website: https://t.co/62vRE0XcBS 🌟Deadline: Oct 20, 2025 🌟8-page research paper / 4-page position paper (including references) Our
llm4code.github.io
ICSE 2026 Workshop on Large Language Model for Code
0
2
24
Announcing the 3rd workshop on #LLM4Code, co-located with @ICSEConf 2026 in Rio de Janeiro, Brazil 🇧🇷! 🎯We are calling for submissions: 🌟Website: https://t.co/Ai3nseQVKP 🌟Deadline: Oct 20, 2025 🌟8-page research paper / 4-page position paper (including references)
3
4
11
📢 The 10th Midwest Security Workshop is coming up! 🗓️ Sat, Sept 20, 2025 📍 Indiana University, Bloomington ✅ Free registration (by Aug 28) Spread the word—please share with anyone interested! - Website: https://t.co/fDbcolT0q6 - Registration: https://t.co/3v7DOo04oa
0
6
13
Very excited to share this update about our team's work on AI for security! Joint work with @miltos1 @xennygrimmato_ @dancherp and many others from GDM and Google Project Zero! To learn more about our agent Big Sleep, check out this blog post:
New from our security teams: Our AI agent Big Sleep helped us detect and foil an imminent exploit. We believe this is a first for an AI agent - definitely not the last - giving cybersecurity defenders new tools to stop threats before they’re widespread.
0
4
42
Check our new #ICML25 paper on learning and refining code transformation rules for code optimization, decompilation, and secure code rewriting!
🚨 EditLord: New #ICML paper on code editing! Software maintenance accounts for 60% of the software lifecycle, and much of it involves code editing. ⚡️ Developers optimize code efficiency 📖 Reverse engineers refactor decompiled mess 🛡️ Security teams mitigate vulnerabilities 🧵
0
2
32
We're excited to invite you to attend DLSP 2025, co-located with IEEE S&P on May 15! https://t.co/Ot5Z7RGjXC Themes: + Security & Privacy for ML + ML for Security & Privacy Invited speakers include: + David Wagner (UC Berkeley) + Yuan Tian (UCLA) + Anoop Singhal (NIST) More
1
7
41
@slow_developer @ceobillionaire The full video https://t.co/jgxTaawUOT 1) Best LLMs including Claude models have < 10% accuracy on difficult coding tasks https://t.co/dbGZsV5uSH and 2) building software is more than coding (we need to set requirements, design, write tests, maintain software, and more).
Can #LLMs replace developers? Introducing RepoCod-Lite 🐟 for faster evaluation to answer this: 200 of the toughest #RepoCod #code-generation tasks: - GPT-4o and other LLMs have < 10% accuracy/pass@1 on RepoCod-Lite tasks - Leaderboard https://t.co/DRPs3attHb - 67
0
2
12
🚀 We're thrilled to announce vLLM Production Stack—an open-source, Enterprise-Grade LLM inference solution that is now an official first-party ecosystem project under vLLM! Why does this matter? A handful of companies focus on LLM training, but millions of apps and businesses
4
26
56
LLMs demonstrate impressive code generation abilities, but do they truly understand execution flow? In our paper, CoCoNUT, we evaluate seven SOTA LLMs on their ability to trace code execution, revealing significant limitations. #LLMs #CodeReasoning
3
3
24
We're excited to announce #callforpapers of the IEEE/ACM International Symposium on Quality of Service (#IWQoS'25). It will be at the Gold Coast, Australia 2–4 July 2025. Share your insights in this field and submit your work! @IEEEComSoc
https://t.co/7i254OY3CQ
iwqos2025.ieee-iwqos.org
Submit a Paper
0
2
3
The 8th Deep Learning Security and Privacy workshop co-located with IEEE S&P @IEEESSP May 15, 2025, San Francisco ( https://t.co/valTC624Yq) is calling for papers, posters and talks! The workshop seeks your awesome contributions on all aspects of deep learning and security, aiming
0
9
44
We wish everyone Happy Holidays! The Binary Analysis Research (BAR) Workshop is happening again with @NDSSSymposium. About 3 weeks to go until the deadline: https://t.co/H2Pnz8p9XE! We welcome short or long papers on *all* things binary analysis! Deadline: Jan 15, 2025 AoE!
1
8
25
I am excited to attend #NeurIPS2024 🤩! I’ll be presenting SimPO and CharXiv, and would love to catch up and chat about: - RLHF, reasoning, high-quality data synthesis and generally about AI! - And.. also about the academic and industry job markets!
9
20
193
3DL is recruiting PhD students to start in Fall 2025! A thread👇highlighting some of our recent works, and what we are excited to explore next 🚀 Apply by Dec. 16; more info: https://t.co/WyvimLwjXe 1/
1
14
42