Jonathan Fürst @JF87

Researcher in IoT, ML, Data Management. Assoc. Prof. @ZHAW, previously Researcher @ NEC Labs Europe, PhD @ITUkbh jofu.org Zurich, Switzerland Joined November 2007

Tweets

2K
Followers

183
Following

806
Likes

725

Jonathan Fürst @JF87

6 days ago

Thanks for the interest in our work. Find out more about it on leaner-ai.com and feel free to contact us!

Which GPU should run your LLM? Most teams answer with a spec-sheet reflex — TDP or TFLOPS-per-watt — and new arXiv (2607.02391) from @La_UPM and @ZHAW, by @maufadel and @JF87, shows both heuristics routinely pick the wrong hardware. WattGPU predicts the two numbers that quietly

2 1 4 260 2

0 0 1 53 0

View Details

Jonathan Fürst @JF87

8 months ago

@shloka_2 Nice that you enjoyed our work :-)

1 0 1 27 0

View Details

Sumit @_reachsumit

9 months ago

VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents Proposes a framework that explicitly models document versioning through hierarchical graphs. 📝arxiv.org/abs/2510.08109 👨🏽‍💻github.com/danielhuwiler/…

0 1 8 596 7

View Details

Jonathan Fürst @JF87

10 months ago

3/ 🔧 Try it yourself: GitHub: github.com/gayecolakoglu/… 📄 Paper: arxiv.org/pdf/2502.18179

0 0 0 24 0

View Details

Jonathan Fürst @JF87

10 months ago

2/ Our OFAT (one-factor-at-a-time) method achieves near-optimal results with just ~2.8% of the computational cost of full factorial search. Result: 13-37 point F1 improvements over baseline configs 📈

1 0 0 22 0

View Details

Jonathan Fürst @JF87

10 months ago

🎉 Our paper "Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs" has been accepted to #EMNLP2025! Ever struggled with LLM-based PDF extraction in your org? This one's for you! 🧵👇

1 0 1 82 0

View Details

Towards Data Science @TDataScience

2 years ago

Want to design better Text-to-Query systems? SM3-Text-to-query is your new go-to benchmark, offering a comprehensive evaluation across different query languages. Read more from @JF87. #LLM #SQL towardsdatascience.com/can-llms-talk-…

1 3 7 2K 5

View Details

Jonathan Fürst @JF87

2 years ago

Happening now. Q&A with Jeff Dean and team on Gemini and the new Gemini 2.0 Flash #NeurIPS2024

0 1 2 319 0

View Details

Towards Data Science @TDataScience

2 years ago

Introducing SM3-Text-to-query: The first dataset to evaluate cross-query language and cross-database models for Text-to-Query systems. @JF87 compares text-to-query capabilities of LLMs in his newest article. #LLM #SQL towardsdatascience.com/can-llms-talk-…

0 4 11 3K 7

View Details

Jonathan Fürst @JF87

2 years ago

5/ More Details: Paper: arxiv.org/abs/2411.05521 Code & Data: github.com/jf87/SM3-Text-… See you in Vancouver! Happy to hear feedback and discuss how we can push Text-to-Query research forward. 🌟 #NeurIPS2024 #NeurIPS #AI #TextToQuery #MedicalAI #LLM @ZHAW @DataScienceCH

0 0 1 107 0

View Details

Jonathan Fürst @JF87

2 years ago

4/ Extensible Design: SM3-Text-to-Query can be easily extended for additional query languages, actual patient databases, or multilingual questions. Stay tuned for more! 😉

1 0 0 62 0

View Details

Jonathan Fürst @JF87

2 years ago

🚀 While I am already packing my bags for Vancouver ✈️, I want to share that we will present SM3-Text-to-Query (arxiv.org/abs/2411.05521) at the NeurIPS'24 Datasets and Benchmarks Track! Here's a quick teaser. 🧵

1 0 0 379 1

View Details

Chris Bakke @ChrisJBakke

2 years ago

Pretty crazy that Google Gemini is only a team of 47 people. 2 engineers 16 PMs 29 senior global directors of DEI

332 2K 26K 2.2M 1K

View Details

Jonathan Fürst @JF87

3 years ago

@_richtig_falsch @TechDialectic Das kann nicht sein…

0 0 2 514 0

View Details

Jonathan Fürst @JF87

3 years ago

@Tiefseher Und das bei zusätzlichem Bevölkerungszuwachs!

0 0 1 64 0

View Details

Bindu Reddy @bindureddy

3 years ago

One the biggest issues with this AI safety stuff is censorship You can’t ask ChatGPT anything remotely controversial or have it generate photos that are routinely posted on Insta to millions of likes ChatGPT is way more censored than an internet search!! 🤯🤯 Why? How does that make sense?