🩸 Interested in compact token representations for complex 3D vessel-like biomedical graphs?
Then check out our latest work, “VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation”, accepted to ECCV 2026!
Day 3 of our advent calendar, showcasing an Escape Room project where our #research group leader Ksenia Keplinger, who leads our Organizational Leadership and #Diversity Group, studies team dynamics. As the game master, she monitors several participants solving puzzles #KI#AI
Llama 2 is now available — open source, free for research and commercial use. These models are accessible to individuals, creators, researchers and businesses.
Download ⬇️
🗣️In a new blog post, we - @projekt_sparta - examine #toxicity levels in Tweets related to the #Midterms2022 and during the takeover by #Musk. Spoiler alert 😱: Toxicity spiked in late October! Check out the full analysis here: https://t.co/bWZ7m6eAyR
Publication Alert 🎊: As of today, our dataset with the Twitter handles of all candidates in the 2022 state election in North Rhine-Westphalia is available here: https://t.co/XTM1NDHltv
Several sources reported that the usage of the #NWord increased radically shortly after #Musk took over Twitter. We @projekt_sparta followed up on this: Despite a drop over time, the term is still used comparatively more often now than before the change in leadership. #HateSpeech
Wenn ihr mehr darüber wissen wollt, welche spannenden Sachen wir @projekt_sparta@unibw_m erforschen, dann ist dieser tolle Beitrag in der @FZ_RISK Jahresbroschüre unbedingt lesenswert! #twitter#Analytics
Mehr #HateSpeech seit #Musk? Am 28.10. berichtete die Washington Post auf Basis von @ncri_io, dass die Verwendung des Begriffs "N*gger" in Tweets kurz nach der Verkündung des Kaufs der Plattform durch Elon Musk um ein Vielfaches gestiegen ist. Aber wie ging es danach weiter?
This is a comprehensive list of the must-read papers on the recent progress of self supervised NLP models (or impressive capabilities of LLMs) and great summary slides!
I also love the role-playing paper-reading seminar fromat! 👩🏽🔬 (https://t.co/ydNANw0Smt)
Matrix factorizations are the pinnacle results of linear algebra.
From theory to applications, they are behind many theorems, algorithms, and methods. However, it is easy to get lost in the vast jungle of decompositions.
This is how to make sense of them.
We've started the Fall 2022 edition of:
🎓CMU CS11-711 Advanced NLP!🎓
Follow along for
* An intro of core topics
* Timely content; prompting, retrieval, bias/fairness
* Content on NLP research methodology
Page: https://t.co/wxXDhSiVqf
Videos: https://t.co/XQPzc6ss99
DALLE-2 was paywall-released recently by an extremely well-funded company.
Just yesterday, a group of independent researchers released their own model (Stable Diffusion) that you can use in a few lines of code for FREE.
The speed of the ML research community is insane 🤯
In calculus, going from a single variable to millions of variables is hard.
Understanding the three main types of functions helps make sense of multivariable calculus.
Surprisingly, they share a deep connection. Let's see why!
Ein weiterer Höhepunkt des Use Case „Elections“ im Projekt SPARTA - unser Nowcasting feiert mit der #NRWLandtagswahl seinen zweiten Geburtstag! Die Stimmung und Themen der Twittersphere zur #nrwltw22 gibt es in Echtzeit auf unserer WebApp:
The first electoral projections of the North Rhine-Westphalian state election are due in 967 hours - Team #SPARTA marks the date with a premiere: our real-time analyses of issues and perceptions of parties/candidates on Twitter are now available at https://t.co/mt37XQTPkj
@Die_Gruenen und @fdp gehen in Sondierungen mit der @spdde. Damit ist der Machtkampf in der @cducsubt eröffnet. Die #PK von @ArminLaschet und die Statements von @_FriedrichMerz gestern Abend sind auf Twitter das große Thema. https://t.co/G5rmvkzS2K