PhD student at Leipzig University https://xitter.cf/t.co/4rBov6VsvV

Joined January 2016
Sebastian Simon retweeted
Session 1 "Engineering AI systems with LLMs", summary of paper 3, with RQ "what do practitioners consider important when using LLMs?"
3
2
152
Just presented our paper "Themes of Building LLM-based applications for Production" at @CAINconf in Ottawa. Find a preprint, including a thematic map of relevant topics when engineering LLM-based systems 🤖, here: arxiv.org/pdf/2411.08574
1
2
5
82
This paper is the result of an excellent collaboration with @__mailach, @Joh4nnesDorn, and @Norbsen.
2
26
Sebastian Simon retweeted
💻⚡ A Survey on Energy-Efficient Software Development. Is it optimized in Practice? What are problems and obstacles? Take this survey to help explore strategies & challenges. ⏳ 10 min for more clarity! 👉 umfrage.uni-leipzig.de/index… #SoftwareEngineering #GreenIT
4
6
233
Sebastian Simon retweeted
Debugging performance bugs is a maze of complexity! Our study uncovers how devs navigate and reason through them, revealing structured debugging episodes. Catch my #FSEconf talk! Preprint, w/@__mailach @SvenApel @JanetSiegmund @RaimundDachselt @Norbsen: sws.informatik.uni-leipzig.d…
4
7
213
Sebastian Simon retweeted
🎉 #CAIN2025 Accepted Submission Spotlight! 🌟 What are practitioners prioritizing for LLM-based systems? From RAG systems to risks, this paper (👥 Authors: Alina Mailach, Sebastian Simon, Johannes Dorn, Norbert Siegmund) maps insights from 189 videos! #LLM #AIEngineering #SE4AI
2
4
183
Sebastian Simon retweeted
🚀 #CAIN2025 Perspectives: @Norbsen Missed the Research & Experience Track? No worries! Submit to one of our other tracks: Doctoral Symposium, Posters, or Industry Talks, before Dec 5, 2024! 🔗 More Info: conf.researchr.org/home/cain… #ICSE2025 #AIEngineering #SoftwareEngineering
2
4
229
Sebastian Simon retweeted
Thanks everyone at #FOSD2024 for the great talks and discussions!
4
11
774
Sebastian Simon retweeted
I’m gonna give 10 random people that repost this and follow me $25,000 for fun (the $250,000 my X video made) I’ll pick the winners in 72 hours
368,920
2,485,704
220,007
1,832,859
286,746,635
Congratulations! 🎉 ScaDS.AI researcher @__mailach has made it into the top 10 applicants for the @ZEISS_Group Women Award. The Award recognizes ambitious female graduates in the field of Digital & IT. 👉 Find out more about her research: sws.informatik.uni-leipzig.d…
1
10
519
Sebastian Simon retweeted
CAIN23 #Session Training & Learning "Exploring Hyperparameter Usage and Tuning in Machine Learning Research" conf.researchr.org/program/c…
1
4
433
We analyzed hyperparameter usage and tuning in 2000 ML code repositories and associated research papers! I am excited to present Nikolai Kolyada, @christopher @martinpotthast, @bennostein, @norbsen, and my work later @CAINconf. Join us if you want to learn more about it!
1
3
9
815
We are also grateful for being nominated for the distinguished paper award! Find the preprint here: bit.ly/3M6wNQT
3
60
Congratulations to our ScaDS PIs @martinpotthast and @Norbsen as well as to our collegue @christopher for being nominated for Best Paper Award @CAINconf! 🚀
CAIN 2023 Candidates for Best Paper Award: CAIN 2023 pre-selected 4 candidates for the Best Paper Award. The winner will be announced during the conference 😉
3
7
561
Happy that our paper has been pre-selected as a candidate for the best paper award. #CAIN2023
CAIN 2023 Candidates for Best Paper Award: CAIN 2023 pre-selected 4 candidates for the Best Paper Award. The winner will be announced during the conference 😉
1
7
449
Sebastian Simon retweeted
#FOSD23 is now officially closed. We had a great week with excellent talks and discussions. Thanks a lot to the keynote speakers, participants, and everyone involved.
7
19
1,215
Sebastian Simon retweeted
Today at 7pm, the 14th edition of the Meeting on Feature-Oriented Software Development #FOSD23 will start at this beautiful villa in Ulm, Germany. The schedule for tomorrow is now available at the website: fosd23.uni-ulm.de/#talks
8
19
1,003
Sebastian Simon retweeted
Does more data always reduce the uncertainty in performance-influence models and what can we learn from options with unreliable performance influence? Find out in our recently accepted @emsejournal paper with @SvenApel and @Norbsen! Preprint: se.cs.uni-saarland.de/public…
7
12