Jonathan Fürst

Researcher in IoT, ML, Data Management. Assoc. Prof. @ZHAW, previously Researcher @ NEC Labs Europe, PhD @ITUkbh

[Jonathan Fürst @JF87]

🚀 While I am already packing my bags for Vancouver ✈️, I want to share that we will present SM3-Text-to-Query (https://t.co/voNbgNHJZV) at the NeurIPS'24 Datasets and Benchmarks Track! Here's a quick teaser. 🧵

[Jonathan Fürst @JF87]

@shloka_2 Nice that you enjoyed our work :-)

[Sumit @_reachsumit]

VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents

Proposes a framework that explicitly models document versioning through hierarchical graphs.

📝https://t.co/qmmS8eitjF
👨🏽‍💻https://t.co/yoi6Sycwn9

[Jonathan Fürst @JF87]

3/ 🔧 Try it yourself: GitHub: https://t.co/FkG2mYuXvx 📄 Paper: https://t.co/yGeNa0A8EH

[Jonathan Fürst @JF87]

🎉 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! 🧵👇

[Jonathan Fürst @JF87]

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 📈

[Towards Data Science @TDataScience]

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

https://t.co/YlV1HgR9xk

[Jonathan Fürst @JF87]

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

[Towards Data Science @TDataScience]

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

https://t.co/YlV1HgR9xk

[Jonathan Fürst @JF87]

5/ More Details:

Paper: https://t.co/voNbgNIhPt
Code & Data: https://t.co/2lfAO9rVTU

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

[Jonathan Fürst @JF87]

🚀 While I am already packing my bags for Vancouver ✈️, I want to share that we will present SM3-Text-to-Query (https://t.co/voNbgNHJZV) at the NeurIPS'24 Datasets and Benchmarks Track! Here's a quick teaser. 🧵

[Jonathan Fürst @JF87]

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! 😉

[Chris Bakke @ChrisJBakke]

Pretty crazy that Google Gemini is only a team of 47 people.

2 engineers

16 PMs

29 senior global directors of DEI

[Jonathan Fürst @JF87]

@_richtig_falsch @TechDialectic Das kann nicht sein…

[Jonathan Fürst @JF87]

@Tiefseher Und das bei zusätzlichem Bevölkerungszuwachs!

[Bindu Reddy @bindureddy]

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?

[Jonathan Fürst @JF87]

@emilymbender Mhm, we don’t really know that. This is just a press release by Microsoft. Like what are the exact rules and scope of this trial is not clear. In the end it is probably more marketing than anything else.