Sharven Wong

@Ming_happylife Thx!

@SharvenW ming-xu-research.github.io/files/Rule_Gen…

🎉Happy to share that our paper “RulePilot: An LLM-powered Agent for Security Rule Generation and Conversion” has been accepted by ICSE’26. This work helps SOC centers to address operational needs with the powerful GenAI techniques. Open-sourced: github.com/LLM4SOC-Topic/…

Our paper "Fault Localization from the Semantic Code Search Perspective" is now abailable on ACM Transactions on Software Engineering and Methodology dl.acm.org/doi/10.1145/37… Hope you will find it an interesting paper to read!

@chao_peng_ @Trae_ai awesome!

🎉 Excited to share our latest work from @Trae_ai Research Team: Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling! We introduce the first agent-based ensemble reasoning framework for repository-level issue resolution, addressing challenges of large search spaces and repo-scale understanding. 🏆 #1 on SWE-bench Verified (75.2% Pass@1) 🧠 Modular design: generation, pruning, selection 🔬 Strong gains across 3 leading LLMs 🌟 GitHub: github.com/bytedance/trae… 📄 Paper: arxiv.org/abs/2507.23370 Huge thanks to everyone who contributed and supported this journey! #AI #LLM #SoftwareEngineering #SWEbench #OpenSource #Trae

@jennytliang Have read this interesting study, but missed the opportunity to meet in Norway

Can prompts be programs? 📝🤔 In some cases, yes! In our #FSE25 work, we explore the future of developers writing "natural language programs" by developing a theory of prompt programming. I'm presenting this work today at 12PM in Cosmos 3B. Come watch or find me during FSE. 👋

@yscnju A pity missing the opportunity to meet so many old friends in Norway

FSE & ISSTA 2025 @🇳🇴

@softwaronnie @ConfEASE Congrats! BTW, Is there any list of this year's distinguished reviewers and papers? 😀

I received the Distinguished Reviewer Award for my contribution to @ConfEASE 2025 in Istanbul. EASE was the first international conference I attended as a master’s student, so being recognized now makes this especially meaningful.

@NavinaHeyden @yyfxlpqf Glad to hear you are travelling in Shanxi. Will you stay in Taiyuan?

@yyfxlpqf It's 山西. If I want to refer to 陕西 I would write it like "Shaanxi"

People from Shanxi really love sour stuff 😅

@my_cat_can_code Wow, Mexico is amazing!

Back from #NAACL2025 -- where tech met culture in the best way: - Ethics & trust took important stage: many works felt like a live debate on how we build, not just what. - Linguistic anthropologists wowed us with stories of endangered dialects -- proof that human context > raw tokens. - Data-efficiency hacks (think RL-on-thought + edge inference) are quietly cutting cloud bills. Recharged by Albuquerque's murals, desert light, and extra-hot chile 🌶️, ready to brew new ideas. What cultural lens do you wish more AI projects embraced?👇

@Gerope90 Thrilled to win this distinguished paper award😊

Congratulations to all awardees

Hi ICPC Community, we just announced the Distinguished Paper Award! #ICPC25 #ICSE2025

@PinjiaHE Congratulations!

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/

As we prepare for #icse2025 in Ottawa, the #icse2026 team is excited to announce that the call for papers for Cycle 1 is open! Deadlines: March 7 (abstracts) & March 14 (submissions). Next year's ICSE will be in Rio de Janeiro (April 12–18). Participate! conf.researchr.org/track/icse-202…

@YiCheng77783310 Congrats! A nice idea👍

🚀 Accepted by ICLR’25! We introduce Integrative Decoding, a novel decoding algorithm to tackle the hallucination problem in LLMs. The core idea is to integrate “self-consistency” into the decoding objective to improve factuality. ✨ Super easy to implement: no training needed, no customized prompt design required. And it has zero restrictions on the generation form, making it a versatile solution for various scenarios. 🧪 We tested it on over a dozen different LLMs and three common benchmarks. The results? Highly stable and significant improvements! 📄 Check out the paper at arxiv.org/pdf/2410.01556 🙏 Big thanks to all our co-authors! @MasterVito0601 @wendyxiao06091 @Yuji_Zhang_NLP @houwenjun060 @xukaish #ICLR2025 #LLM

@Fannyjrd_ Wow, interesting finding!

Happy New Year 1³+2³+3³+4³+5³+6³+7³+8³+9³ (=2025) to all 😋

@aserebrenik @f_sarro @nellybencomo @patricia_lago @ShivaNejati @ComputerSociety Congrats!

It is an honor to be elected. Looking forward to working w @f_sarro @nellybencomo John Grundy @patricia_lago @ShivaNejati Mike Whalen and Tao Zhang!

@Chasen86341870 Haha, I have the same feeling. One of my recent submissions was asked to compare with an arxiv paper that was not released at the time we submitted. 😅

For example, we were requested to add experiments comparing with arXiv papers that have not undergone peer-review and comparing with tools that, although open-source, are not functional for experimentation.

What happened to OOPSLA? 89 out of 143 unrejected? Considering the rejection rate is less than 50%, is it lucky or unlucky that our paper was directly rejected?

@_Lin_Ai_ @JiatengLiu @May_F1_ @juliahberg @hengjinlp @preslav_nakov Congrats!

Excited to share 1/2 of my #coling2025 papers: PropaInsight: Toward Deeper Understanding of Propaganda! Huge thanks to my coauthors @JiatengLiu, @May_F1_ and team, and special thanks to @juliahberg, @hengjinlp, @preslav_nakov for their support! Read here: arxiv.org/pdf/2409.18997

@ye_he_ye @uclcs @f_sarro Congrats!

Excited to join UCL @uclcs as a Lecturer (aka Assistant Professor) starting in Spring 2025. I'm looking forward to collaborating with amazing colleagues @f_sarro, and looking for 25Fall PhD students to work on multimodal agentic coding. If you're interested, drop me an email!

@Fannyjrd_ Wow, 26 with a permanent position. That would be amazing for me!

Is 'early stage researcher' only for PhDs and Postdocs? 🤔 I already have a permanent position but I'm only 26, so I still feel like I need coaching from more senior researchers. And there are often mentoring opportunities for women in AI but I hesitate to apply right now. 😐