We are looking for two postdoctoral researchers in our Explainable Machine Learning group TU München Helmholtz Munich | @HelmholtzMunich ELLIS, application deadline is November 19th (fully funded, flexible starting dates, flexible topics, duration negotiable). More details 👇

a Gradio demo of ReNO is live! AK

Curious about the potential of optimal transport (OT) in representation learning? Join @CuturiMarco's talk at the UniReps workshop today at 2:30 PM! Marco will notably discuss our latest paper on using OT to learn disentangled representations. Details below ⬇️

𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝟮𝟬𝟮𝟰: 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗧𝗵𝗲𝗺𝗲𝘀 𝗮𝗻𝗱 𝗠𝗲𝗺𝗲𝘀 📝 The moment you've all been waiting for... I have a blog! The first post summarises the happenings and trends in diffusion modelling at NeurIPS 2024 from my perspective, including: • Personal

Our work on geometric disentangled representation learning has been accepted to ICLR 2025! 🎊See you in Singapore if you want to understand this gif better :)

Great to see this work being accepted at #ICLR2025 - it provides a wonderful new perspective on disentanglement through the lens of optimal transport!

Good to see moscot finally published in nature! Check out the paper (tinyurl.com/33zuwsep), the research briefing (tinyurl.com/mrvpbkpj), and moscot-tools.org to learn more about it!

Intrigued? Also go check out our follow-up work @NeurIPS (tinyurl.com/2s4uc48f) w Théo Uscidda and @ICLR24 w Luca Eyring, Théo Uscidda (tinyurl.com/2r4824fv) how to bring neural networks into this.

Check out our work on how Quadratic Optimal Transport can help enhance Disentangled Representation Learning! Now accepted at #ICLR2025, see you in Singapore :) Full details in the thread below! 👇

Controlling Latent Diffusion Using Latent CLIP "In this paper, we introduce Latent-CLIP, a CLIP model that operates directly in the latent space. We train Latent-CLIP on 2.7B pairs of latent images and descriptive texts, and show that it matches zero-shot classification

Exciting to share that we have 4 papers to be presented in the coming #ICLR2025 in the beautiful city of #Singapore . Check out our website for more details: eml-munich.de/publications. We will introduce the talented authors with their papers very soon, stay tuned🤓.

🌏 #ICLR2025 is coming to the beautiful city of Singapore — April 24–28! We're excited to share 4 upcoming papers being presented at the conference. Check out the thread for highlights, and come chat with the authors if you're interested! 🧵👇

(3/4) Disentangled Representation Learning with the Gromov-Monge Gap A fantastic work contributed by Théo Uscidda and Luca Eyring , with Karsten Roth, Fabian Theis, Zeynep Akata, and Marco Cuturi. 📖 [Paper]: arxiv.org/abs/2407.07829

📢 We’ve landed in Singapore for #ICLR2025! The EML group is presenting 4 exciting papers — come say hi at our poster sessions! 👇Let's chat! More details in the thread — see you there! 🌟

Massimo Bini shuchen wu (4/4) Disentangled Representation Learning with the Gromov-Monge Gap Luca Eyring will present GMG, a novel regularizer that matches prior distributions with minimal geometric distortion. 📍 Hall 3 + Hall 2B #603 🕘 Sat Apr 26, 10:00 a.m.–12:30 p.m.

Catch me at #ICLR2025 today - I’ll be presenting our work on Quadratic OT for Representation Learning, the Gromov-Monge Gap, at Hall 2B, poster #603 during the morning session (10:00–12:30)!

#CVPR2025 is heading to the 'Music City' — Nashville! 🎺 Join us from June 11–15. We're thrilled to announce that we'll be presenting four papers at #CVPR2025! Check out the thread below for highlights, and feel free to stop by and chat with our authors! 📷👇

🎓PhD Spotlight: Shyamgopal Karthik Celebrate Shyamgopal Karthik , who will defend his PhD on 23rd June! Shyam has been a PhD student Universität Tübingen since October 2021, supervised by Zeynep Akata. His research has been centred around compositionality in vision and language. In