ML researcher, Musician. Founder of @clashingseats, personal: https://xitter.cf/t.co/QkYGZkDas6
Berlin, Deutschland
Joined March 2009
- Tweets50
- Following267
- Followers102
- Likes87
Thomas Schnake retweeted
We have a new paper on diffusion!📄
Faster diffusion models with total variance/signal-to-noise ratio disentanglement! ⚡️
Our new work shows how to generate stable molecules in sometimes as little 8 steps and match EDM’s image quality with a uniform time grid. 🧵
Thomas Schnake retweeted
❓ Do histopathological foundation models eliminate batch effects? ❓
The surprisingly clear answer is: they do not!
Find out more in our new paper that we will present at the AIM-FM Workshop at @NeurIPSConf.
Link: arxiv.org/abs/2411.05489
Thomas Schnake retweeted
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…
Thomas Schnake retweeted
Big thanks to my collaborators and mentors, first and foremost @IdajiMina, as well as @EberleOliver, @thomschnake, @jdppel, @lciernik, Oliver Buchstab, @am0ck, Frederick Klauschen, Klaus-Robert Müller, and all the supporters from @bifoldberlin and @ml_tuberlin.
Thomas Schnake retweeted
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology by @hense96 @IdajiMina @EberleOliver @thomschnake @jdppel @lciernik , Oliver Buchstab, @am0ck , Frederick Klauschen, Klaus-Robert Müller
Thomas Schnake retweeted
✨ Our xMIL paper has been accepted at #NeurIPS2024 ✨
arXiv preprint: arxiv.org/abs/2406.04280
Thomas Schnake retweeted
🥳👏Warmest congratulations to BIFOLD scientist Dr. Alexander von Lühmann, who was awarded an ERC Starting Grant of EUR 1.65 million. We are very proud and excited for him and his entire team!!🍾 Read more: bifold.berlin/news-events/ne…
Thomas Schnake retweeted
Check out our new position and review paper on representational alignment. We try to find common language across research disciplines, provide a general formal framework, review the existing literature, and discuss open challenges. Amazing team effort!!! 🤖🧠
🧵🎉 Our new preprint is up, and we’d love your feedback! We're "Getting Aligned on Representational Alignment" - the degree to which internal representations of different (biological & artificial) information processing systems agree. 🧠🤖🔬🔍 #CognitiveScience #Neuroscience #AI
Thomas Schnake retweeted
We are currently preparing the call for papers for Re-Align: The First Workshop on Representational Alignment at #ICLR2024! You can shoot me a DM (or fill out the form below👇) if you want to be on the reviewing committee.
⏳⏰Details about our #ICLR2024 workshop on Representational Alignment 🧠🤝🧠 are coming very soon!
For now, RSVP to receive updates - forms.gle/NsAsRgZu7kPj8qWL6
(Or frantically check the website every couple of days 😅 - representational-alignment.g… )
Thomas Schnake retweeted
We're excited to present our paper "Fast and Unified Path Gradient Estimators for Normalizing Flows" at #ICLR2024 in two weeks! 🎉 This work focuses on deriving efficient gradient estimators for coupling-type normalizing flows using the inverse function theorem.
Thomas Schnake retweeted
Faithful attributions are measured by pixel flipping!
But how trustworthy and consistent are the PF benchmarks?
Read our new preprint to learn more!
@nstrodt @jvielhaben
@ml_tuberlin @bifoldberlin @FraunhoferHHI #XAI #diffusion
arxiv.org/abs/2401.06654
Hey @gklambauer
thanks for reposting. For me as an author the preparation was a great experience!
If you have any questions #symbolicXAI #symbXAI feel free to ask me directly.
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Abstractions on top of traditional XAI methods are used. These are combined with logical operators to provide explanations...
P: arxiv.org/abs/2408.17198
Thomas Schnake retweeted
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Abstractions on top of traditional XAI methods are used. These are combined with logical operators to provide explanations...
P: arxiv.org/abs/2408.17198
Thomas Schnake retweeted
🎉Our preprint <<Towards Symbolic XAI>> came out!
Next to classic ML stuff like NLP, we have a chemistry section! ⚗️
What's going on inside a neural network while it's predicting molecular properties?
arxiv.org/abs/2408.17198
Thomas Schnake retweeted
📢 New Preprint Alert 🚨
Ever Wondered How to Make Mamba Models More Transparent?
Meet MambaLRP🔥
We introduce MambaLRP, a novel algorithm within the Layer-wise Relevance Propagation (LRP) framework, specially designed to enhance the explainability of Mamba models.
1/7
Enjoying my visit at Chemical Compound Space Conference (CCSC) in Heidelberg. #chemistry #machinelearning
Mhh... where does that come from?
heise.de/news/Machtkampf-bei…
Thomas Schnake retweeted
We have a new website 🎉
Thanks to all the people who put countless hours into making it look as amazing as it does!
Want to learn more about our team, #research, open positions and offered courses?
Check it out 👉 web.ml.tu-berlin.de
#MachineLearning #Berlin
It was a great honor to be the opening speaker of the @dida_ML conference in April. I presented some of my latest research work entitled "Extending Explainable AI". The video recording of the talk is now available 👇
youtube.com/watch?v=X_Qjl8qL…
#AI #MachineLearning #XAI