@ml_tuberlin

This is the Machine Learning Group of Prof. Klaus-Robert Müller @TUBerlin. Proud part of @bifoldberlin.

 Berlin, Deutschland
web.ml.tu-berlin.de
Joined June 2023
  • Tweets72
  • Following70
  • Followers633
1Media
This is the #MachineLearning Group of Prof. Klaus-Robert Müller at the @TUBerlin. Let’s connect! #ScienceTwitter
7
4
34
5,393
ML Group, TU Berlin retweeted
BIFOLD@bifoldberlin3 Dec 2024
The Machine Learning group of BIFOLD Co-Director Klaus-Robert Müller will be represented at the @NeurIPSConf with 8 puplications. More: bifold.berlin/news-events/ne… @TUBerlin @ml_tuberlin
Several BIFOLD research groups actively contribute to the program of the 48th Annual Conference on Neural Information Processing Systems (NeurIPS 2024), held in Vancouver, Canada, from December 10-15, 2024. The Machine Learning group of BIFOLD Co-Director Klaus-Robert Müller alone is represented at the conference with 8 puplications. NeurIPS covers a wide range of topics with machine learning and neuroscience, including cognitive science, psychology, computer vision, statistical linguistics, and information theory.

ALT Several BIFOLD research groups actively contribute to the program of the 48th Annual Conference on Neural Information Processing Systems (NeurIPS 2024), held in Vancouver, Canada, from December 10-15, 2024. The Machine Learning group of BIFOLD Co-Director Klaus-Robert Müller alone is represented at the conference with 8 puplications. NeurIPS covers a wide range of topics with machine learning and neuroscience, including cognitive science, psychology, computer vision, statistical linguistics, and information theory.

1
2
646
🔊 We have a new preprint on the consistency of representational similarities in #ComputerVision models like #ImageNet ! Check it out! 🔬 #MachineLearning #AI
Laure Ciernik@lciernik11 Nov 2024
If two models are more similar to each other than a third on ImageNet, will this hold for medical/ satellite images? Our preprint analyzes how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7
1
6
948
🔊 Check out one of our latest #NeurIPS2024 publications on #XAI for state space sequence models! #MachineLearning #AI
Farnoush Rezaei-Jafari@FarnoushRJ4 Nov 2024
🎉 Thrilled to announce that our paper MambaLRP has been accepted at #NeurIPS2024! Explain your Mamba models in a faithful, efficient, and effective way! 🐍 Huge thanks to @EberleOliver, Grégoire Montavon, and Klaus-Robert Müller @bifoldberlin, @ml_tuberlin , @GoogleDeepMind,
7
863
🔊 Check out our latest publication „Historical insights at scale: A corpus-wide machine learning analysis of early modern astronomic tables“. Now out in @ScienceAdvances 🎉 Together with @bifoldberlin @MPIWG #MachineLearning #AI #History
Oliver Eberle @eberleoliver.bsky.social@EberleOliver28 Oct 2024
Our work on historical insights at scale using machine learning is now out in @ScienceAdvances! Very proud of this team effort, bridging disciplines and institutions—@MPIWG @TUBerlin @bifoldberlin @ml_tuberlin 📜science.org/doi/10.1126/scia…
1
12
626
🔊 Finally online and accepted at #NeurIPS24! Congratulations to the whole team 🎉 #MachineLearning #AI #ComputerVision #HumanAlignment
Lukas Muttenthaler@lukas_mut15 Oct 2024
Which tasks benefit the most from aligning vision models with human perceptual judgments? In our most recent NeurIPS paper we pin down the downstream tasks where perceptual alignment yields the strongest increases in performance. More in the thread below 👇
1
11
956
🔊 #PhDPosition in #MachineLearning available! Come join our lab at @TUBerlin and @bifoldberlin and work on #XAI and #Ai4Science 🧬🧠
BIFOLD@bifoldberlin11 Oct 2024
#Job for #PhDCandidates: Develope and implement #XAI methods for ML models in Quantum Chemistry. BIFOLD is seeking a Research Associate in #ML for a project supervised by Dr. Stefan Chmiela and Dr. Shinichi Nakajima. Apply by 7th Nov '24 linkedin.com/jobs/view/40470… @ml_tuberlin
Independent and responsible research in the field of machine learning. The goal of the advertised project is the development of new explanation methods (Explainable Artificial Intelligence, XAI) for atomistic modeling in quantum chemistry. The focus is on acquiring physically grounded insights to guide hypotheses in quantum chemistry.

ALT Independent and responsible research in the field of machine learning. The goal of the advertised project is the development of new explanation methods (Explainable Artificial Intelligence, XAI) for atomistic modeling in quantum chemistry. The focus is on acquiring physically grounded insights to guide hypotheses in quantum chemistry.

6
15
1,877
🔊 Check out our latest pre-print! We present SO3LR, a machine learned force field for the simulation of all four major types of biomolecules 🧬 #MachineLearning #CompChem #MolecularDynamics #ForceFields
Adil Kabylda
@kabylda_8 Oct 2024
Couldn't have asked for better timing #NobelPrize Our new work on 'Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields' is now out on @ChemRxiv! #MachineLearning #compchem
2
9
2,607
🔊 Proud that our lab has four #NeurIPS2024 publications this year! 🎉 Check them out 👇 #MachineLearning #Artificalintelligence
4
1
15
1,461
MambaLRP: Explaining Selective State Space Sequence Models by @FarnoushRJ , Grégoire Montavon, Klaus-Robert Müller, @EberleOliver
4
424
CoSy: Evaluating Textual Explanations of Neurons by @lkopf_ml @BommerPhiline @anna_hedstroem @SLapuschkin @Marina_MCV @kirill_bykov
5
273
Federated Learning over Connected Modes by @dgrinwald93 @PhilippWiesner , Shinichi Nakajima
1
5
241
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology by @hense96 @IdajiMina @EberleOliver @thomschnake @jdppel @lciernik , Oliver Buchstab, @am0ck , Frederick Klauschen, Klaus-Robert Müller
2
3
536
🔊 Check out the two new pre-prints, presenting the results from the TEA Challenge 2023 on crash testing #MachineLearning #ForceFields 🧬 #QuantumChemistry #ComputationalChemistry
TCPUniLu@TCPUniLu30 Sep 2024
The results of the ☕️TEA Challenge 2023 and subsequent one-year investigations are now available as @ChemRxiv preprints in two parts👇1/3
4
13
1,726
🔊 Check out one of our latest publications, which has been accepted at #NeurIPS2024! Congrats to the whole team! 🎉
Julius Hense@hense9630 Sep 2024
✨ Our xMIL paper has been accepted at #NeurIPS2024 ✨ arXiv preprint: arxiv.org/abs/2406.04280
9
582
🔊 New pre-print together with @GoogleDeepMind and @bifoldberlin on human alignment of vision models. Congrats to all people involved 🎉 #MachineLearning #AI #Alignment
Lukas Muttenthaler@lukas_mut13 Sep 2024
Really excited to share what we’ve been working on for the past 12 months during my time @GoogleDeepMind! We came up with an approach that can distill the hierarchical structure of human conceptual knowledge into vision foundation models via a surrogate teacher model. More below!
1
6
1,323
🔊 Check out our latest pre-print! Congrats to the whole team! 👏 #Neuroscience #AI
This Post is from an account that no longer exists. Learn more
4
7
3,119
🔊 New publication in @TmlrOrg Decoupling Pixel Flipping and Occlusion Strategy for Consistent #XAI Benchmarks, by @sbluecher @jvielhaben and @nstrodt together with @bifoldberlin and @FraunhoferHHI 🙏🏼 #MachineLearning #AI
Stefan Blücher@sbluecher8 Jul 2024
Greatful to be published @TmlrOrg. Thanks to @nstrodt and @jvielhaben for their support. @bifoldberlin @ml_tuberlin @FraunhoferHHI
1
4
11
1,307
🎉🏆 Congratulations to our PhD student Parastoo for winning the “Best Poster Presentation”-Award at the CSC 2024! #MachineLearning #Catalysis
BIFOLD@bifoldberlin17 May 2024
🥳Many congratulations to Parastoo Semnani, member of the BIFOLD Graduate School, who won the "Best Poster Presentation"-Award at the 27th Canadian Symposium on Catalysis (CSC 2024) in Sherbrooke.
7
593
🔉 Check out our latest paper on the intersection of #XAI and #NLP together with @bifoldberlin! #NAACL24 #MachineLearning
Oliver Eberle @eberleoliver.bsky.social@EberleOliver14 May 2024
🚨 Preprint! Our #NAACL24 paper analyzes semantic textual similarity to unveil #LLM strategies via second-order BiLRP explanations. Preprint: arxiv.org/abs/2405.06604 Code: github.com/alevas/xai-simila… #ExplainableAI #NLP @AlexVsl2 @bifoldberlin @ml_tuberlin @TUBerlin @naaclmeeting
Pairs of semantically similar sentences from the STSb dataset are explained using relevant token interactions.

ALT Pairs of semantically similar sentences from the STSb dataset are explained using relevant token interactions.

2
5
837
🔉 We are at #ICLR2024 in #Vienna with 3 #posters and 1 #workshop! Check them out 👇 #MachineLearning #Conference
4
2
8
808
Set Learning for Accurate and Calibrated Models by @lukas_mut @robvdm @richard_qiuyi_z @TomUnterthiner and Klaus-Robert Müller openreview.net/forum?id=HZ3S…
1
1
1
1,133
Visit us: Hall B // Wednesday // May 8th // 10:45 am
303
Load more