Sebastian Baunsgaard retweeted
Proud advisor moment: Today, @SBaunsgaard successfully defended his PhD with a very convincing talk and discussion. 💯 I'm very happy and thankful. ❤️ Also thanks to the external reviewers @cbinnig and Viktor Leis, as well as Volker Markl for heading the committee.
Sebastian Baunsgaard retweeted
✨ Excited to present our workshop paper at DataWorld at #ICML2025 tomorrow 🇨🇦
We introduce the problem of detecting cross-modal errors in tabular data that originate from other modalities.
Visit our poster:
📅 Saturday, July 19, 10:05 AM - 11:20 AM
📍 West Meeting Room 208-209
Sebastian Baunsgaard retweeted
Today, Jonas presents a new type of adversarial examples at @icmlconf!
We exploit subtle numerical differences between linear algebra backends and craft inputs that yield different predictions from the same model depending on the backend used 🤯 mlsec.org/docs/2025-icml.pdf
1/4
ALT Visualization of the attack. A dog is shown for which three backends yield the prediction "boxer", while one backend returns "castle".
Sebastian Baunsgaard retweeted
🎉 Happy to present our spotlight paper at #ICML2025 tomorrow 🇨🇦
We introduce scSSL-Bench, a benchmark evaluating 19 SSL methods across 9 single-cell multi-omics datasets🧬 and 3 tasks.
Visit our poster:
📅 Thu Jul 17, 11 AM - 1:30 PM PDT
📍 West Exhibition Hall B2-B3 #W-311
Sebastian Baunsgaard retweeted
There is a new open call for a PhD position in our DAMS lab group. 🎇🎆 This position is about research on ML system internals (DSL/APIs, compiler, runtime, accelerators) with involvement in teaching.
You can apply until July 18 here
tinyurl.com/hyjertvb
Sebastian Baunsgaard retweeted
📢 Our extended benchmark on self-supervised learning for single-cell data, scSSL-Bench 🧬, is now accepted at ICML (spotlight)!
Thanks to all collaborators from @bifoldberlin and @CSatETH !
📢Our benchmark on self-supervised learning for single-cell data🧬 is accepted at the #NeurIPS2024 SSL workshop. We take a first step towards establishing best practices for SSL methods for single-cell data, and benchmark 8 SSL methods on 3 downstream tasks across 8 datasets.
Sebastian Baunsgaard retweeted
The @SIGMODConf Programming Contest goes into another round. We (Bo Tang, Tilmann Rabl, and myself) just published the timeline and task overview:
sigmod-contest-2025.github.i…
Thanks to @carlo_curino and @Microsoft for the continued support.
Sebastian Baunsgaard retweeted
📢Our benchmark on self-supervised learning for single-cell data🧬 is accepted at the #NeurIPS2024 SSL workshop. We take a first step towards establishing best practices for SSL methods for single-cell data, and benchmark 8 SSL methods on 3 downstream tasks across 8 datasets.
Sebastian Baunsgaard retweeted
Congrats to all the distinguished associate editors and reviewers @VLDB2024 and thanks for the effort - I'm honored and thankful to be on the list as well.
Sebastian Baunsgaard retweeted
🚀 We have a new open position for a PhD student to research generative AI in security and privacy. Fully funded and based in vibrant Berlin!
Apply by September 13: mlsec.org/jobs.html#jobs
@bifoldberlin @TUBerlin
Sebastian Baunsgaard retweeted
Here is David's great work on non-invasive adaptive query processing in @duckdb, which originated from multiple @dagstuhl seminars. We're also working on an actual DuckDB extension to contribute it back.
Vol:17 No:6 → POLAR: Adaptive and Non-invasive Join Order Selection via Plans of Least Resistance vldb.org/pvldb/vol17/p1350-j…
Sebastian Baunsgaard retweeted
📢 Excited to share Feature Clock, an open-source library and paper accepted at @ieeevis! Feature Clock enhances the explainability and compactness of visualizations of high-dimensional effects in two-dimensional plots.
Big thanks to my co-authors @val_boeva and @RSevastjanova!
Sebastian Baunsgaard retweeted
⚠️#JobAlert: Our group at @bifoldberlin is looking for #postdoctoral researchers to join our team. If you are interested in conducting research at the intersection of #machinelearning & #datamanagement for #earthobservation ➡️
Apply before Feb 15th, 2024: jobs.tu-berlin.de/en/job-pos…
Sebastian Baunsgaard retweeted
This semester I did a traveling sabbatical in Europe. Many thanks to Tilmann Rabl, @matthiasboehm7, @peterabcz for giving me a place to crash at their groups & everyone who hosted me for a talk!! Here are the slides & itinerary for the talk:
itu-dasyalab.github.io/RAD/t…
Sebastian Baunsgaard retweeted
The @bifoldberlin doctoral school has a new call for 10 PhD student positions (application deadline: Jan 26, 2024):
jobs.tu-berlin.de/en/job-pos…
bifold.berlin/education/thes…
Sebastian Baunsgaard retweeted
🎇 We have another opening for a PhD student position in the @bifoldberlin agility project 'LungCAIRE' with Charité on multimodal data representations for lung cancer relapse prediction and related use cases:
jobs.tu-berlin.de/en/job-pos…
(application deadline: Sep 08, 2023)
Sebastian Baunsgaard retweeted
Research Paper / Thursday June 22
AWARE: Workload-aware, Redundancy-exploiting Linear Algebra. Sebastian Baunsgaard, Matthias Boehm
dl.acm.org/doi/10.1145/35886…
@SBaunsgaard @matthiasboehm7
Sebastian Baunsgaard retweeted
great opportunity for PhD positions in ML and data management - lots of interesting topics, and depending on the topic, supervised by one or multiple BIFOLD groups.
Are you looking for a PhD in data management or machine learning? The Graduate School of the 'Berlin Institute for the Foundations of Learning and Data' (@BifoldBerlin) at the @TUBerlin is now looking for 10 PhD students. Apply now! bit.ly/3mNdNyt
