Konstantin Kobs retweeted
All good things come in threes: We will present our last paper at #NAACL2024 "The Roman Empire Strikes Back" at the @SemEvalWorkshop poster session at 14:00. Meet us there!
It is a joint work with @konstantinkobs on detecting hallucination detection in text generation models.
Konstantin Kobs retweeted
A PhD student who recently finished her dissertation gave me the book “Big Panda and Tiny Dragon” from James Norbury. This page resonated so much. Does it also apply to your academic journey or would you disagree?
#AcademicTwitter #PhDlife #PhDchat
Konstantin Kobs retweeted
We're pleased to announce the release of our #ChatGPT Plugin🎉
Designed for researchers familiar with BibSonomy.org and those looking to start, this tool grants access to a database of 200M+ scientific publications! (🧵👇🏻1/4)

ALT ChatGPT explaining: "Welcome to the world of seamless scientific research with the Bibsonomy ChatGPT Plugin! Imagine having a personal research assistant that can: • Search for academic papers and authors across multiple platforms like Bibsonomy and Semantic Scholar. • Add, edit, and manage your research papers in your Bibsonomy account. • Find related works to build a comprehensive knowledge graph. • Retrieve detailed information about papers, including abstracts and TL;DRs. • Tailor vour search with filters like year, tags, and more! All of this, right at your fingertips! Say goodbye to endless browser tabs and hello to a streamlined, efficient research experience. Ready to elevate your academic journey? Let's dive in!"
Our paper “CLIP knows Image Aesthetics” is now published. We show that CLIP is a better base for Image Aesthetic Assessment models than ImageNet, providing useful results even in a zero-shot setting. Previous CLIP studies focus on content and not style features. @datascience_jmu
New Research: CLIP knows image aesthetics frontiersin.org/articles/10.… #AI
Konstantin Kobs retweeted
Our paper "InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images" has been accepted at WACV 2023 ift.tt/AMiLPrb
In this paper by K. Kobs, M. Steininger, and A. Hotho, we use language to guide an image embedding process such that the resulting embedding s…
Konstantin Kobs retweeted
Our paper "On Background Bias in Deep Metric Learning" has been accepted to ICMV 2022 ift.tt/rdAajkX
In this paper, we investigate if Deep Metric Learning models are prone to background bias and test a method to alleviate such bias.
I am so excited to announce that our paper "Do Different Deep Metric Learning Losses Lead to Similar Learned Features?" got accepted at @ICCV_2021! 😍 @datascience_jmu
Konstantin Kobs retweeted
PhD student: There's a word limit and I don't know how to cut this paper any shorte...
Senior coauthor:
nitter.cf/DudespostingWs/status/…
Konstantin Kobs retweeted
Please share: We are looking for excellent candidates to fill 4 (open) tenured university professorships at #CAIDAS, the upcoming Center for Artificial Intelligence in Data Science @Uni_WUE!
go.uniwue.de/caidas
#HCI #NLP #ML #MachineLearning #Mathematics #CS
Konstantin Kobs retweeted
Our Discovery Challenge "ChAT - Chat Analytics for Twitch" will be presented next week at @ECMLPKDD 2020. Join us on Friday, Sep 18th, to discuss results and our exciting new Twitch data!
events.professor-x.de/dc-ecm…
Konstantin Kobs retweeted
https://nitter.cf/t.co/Ck9EImdzv3 In this interdisciplinary work with @hci_wurzburg, we present an approach of incorporating biofeedback features (heart rate + brain wave) into text-based sentiment tasks - plus you get to watch the talk! youtube.com/watch?v=rgMR40Ad…
#NLProc #ONION #LREC2020
Konstantin Kobs retweeted
Reviewer two? nitter.cf/JasmineKardde35/status…
Konstantin Kobs retweeted
"Roses are red, violets are blue,
both are somehow similar, but the classifier has no clue."
Watch out for SimLoss, which allows to introduce background #knowledge in the form of class similarities into #NeuralNetwork classifiers! #DataScience #ISMIS2020
dmir.uni-wuerzburg.de/news/s…
Konstantin Kobs retweeted
OpenLUR, an easily and globally applicable land use regression framework for air pollution modelling, got accepted at Atmospheric Environment (@ELSenviron)! 🎉 #DataScience #environmental #research
Konstantin Kobs retweeted
Discover Twitch.tv by analyzing over 200 million stream chat messages. Automatically determine if a user is subscribed to a channel and submit your approach to the “Chat Analysis for Twitch” (ChAT) Discovery Challenge! events.professor-x.de/dc-ecm…
#ecmlpkdd2020
My prediction: Nine months from now, more babies than usual are going to be born. We will call them #coronakids 👶
Konstantin Kobs retweeted
I spent half my day working from home figuring out my VPN
In 1665, the University of Cambridge temporarily closed due to the bubonic plague. Isaac Newton had to work from home, and he used this time to develop calculus and the theory of gravity. cudl.lib.cam.ac.uk/view/MS-A…
Konstantin Kobs retweeted
If only every serious deadline reminder email we receive on a daily basis had some dose of humor and creativity in it, our busy stressful days would have passed easier! Thanks @aclmeeting!! #ACL2020






















