Mixed Models with Multiple Instance Learning (MixMIL) received an Oral & Outstanding Student Paper award at AISTATS Conference last week! 🏆 MixMIL enables accurate & interpretable patient label prediction from single-cell data by adding attention to GLMMs.#singlecell #MachineLearning

📣 This year at #ICML2024 we are hosting ✨ Gram Workshop ✨ Geometry-grounded representation learning and generative modeling. We welcome submissions in multiple tracks i.e. 📄 Proceedings, 🆕 extended abstract, 📝Blogpost/tutorial track as well as🏆 TDA challenge.

Fantastic opportunity for geometry-oriented folks! ✨Our Gram Workshop at ICML Conference 2024 ✨

📢 GRaM will now accept papers (both proceedings and extended abstracts) till 𝟑𝐫𝐝 𝐉𝐮𝐧𝐞 𝟖𝐩𝐦 𝐔𝐓𝐂 !

Equivariant Topological Message Passing goes Cellular 🦎 Check out our latest work on integrating topological and geometric message passing, generalizing the simplicial case to CW complexes!

Have you ever struggled to find 𝑔𝑜𝑜𝑑 papers or understand key contributions in a new research area? Imagine a blog post breaking down complex papers into simple, graspable ideas ✨ Well, now's your chance to write a blog post on papers that inspire you! ✍️ Gram Workshop

Flow Matching goes Variational! 🐳 In recent work, we derive a formulation of flow matching as variational inference, obtaining regular FM as a special case. Joint work with dream team Grigory Bartosh, @chris_naesseth, Max Welling, and Jan-Willem van de Meent. 📜arxiv.org/abs/2406.04843 🧵1/11

We have kicked off! The best summer school on #GenerativeAI: ✨Generative Modeling Summer School 2024✨! We turn TU Eindhoven into the world's capitol of #GenAI. Amazing lineup: Jes Frellsen, Pierre-Alexandre Mattei, Durk Kingma, yingzhen, Heli Ben-Hamu, Stephan Mandt @ AISTATS’25, Ewa Szczurek, Vlado Menkovski 🤩

The 2nd day of the best summer school on GenAI: Generative Modeling Summer School #GeMSS24. After the morning session on ARMs (convs & transformers) given by yours truly, now we have a session on normalizing flows by Jes

After sharing my thoughts on LLMs in the morning, now we have Jes Frellsen introducing energy-based models at the best #GenAI summer school (gemss.ai/2024/) at TU Eindhoven, at the heart of Brainport Eindhoven!

Fantastic lecture on notoriously-hard-to-teach message passing by yingzhen !

Next invited lecturer at the #GenAI summer school (gemss.ai) is the amazing Stephan Mandt @ AISTATS’25 talking about #GenAI for environment! #GeMSS24

𝑮𝒐𝒊𝒏𝒈 𝒘𝒊𝒕𝒉 𝒕𝒉𝒆 𝒇𝒍𝒐𝒘 at the Generative AI summer school #GeMSS2024 at TU Eindhoven ! What a wonderful, well-explained talk on Flow Matching by the brilliant Heli Ben-Hamu 🤩

Easily one of the best talks I attended ever! #Flow_Matching

The last talk of the best #GenAI summer school #GeMSS24 (gemss.ai/2024/): Maurice Peemen (Thermo Fisher) on #GenAI for electron microscopy

Recently, I have been getting more interested in #GenerativeAISystems (#GenAISys). I am convinced that a systems-based perspective on #GenAI is crucial to design more reliable, robust, and responsive #GenAI. You can read my perspective here: arxiv.org/abs/2407.11001

Hello #GRaM enthusiasts, Sadly our previous twitter account has been compromised, and we won't be able to get hold of it soon. Hence, we have moved to our new handle GRaM Workshop at ICML 2024. Kindly unfollow Gram Workshop and follow us GRaM Workshop at ICML 2024 for more information. ICML Conference

Sharvaree Vadgama ✈️ @ICML 2025 GRaM Workshop at ICML 2024 Gram Workshop ICML Conference Follow GRaM Workshop at ICML 2024: Geometry-Grounded Representation Learning and Generative Modeling! We've got an amazing workshop coming up (Sat 27 July, ICML Conference), w many inspiring talks (gram-workshop.github.io/schedule.html), and a beautiful set of contributions to appear in our proceedings! Stay tuned!

🎊 It has arrived 🎊, the 2nd edition of my "Deep Generative Modeling" book. It has 100 new pages, 3 new chapters (incl. #LLMs) and new sections. It covers all deep generative models that constitute the core of all #GenerativeAI techs! Check it out: 💻tinyurl.com/mwj9dw83

🚀 In our latest paper accepted to Accepted papers at TMLR (jmlr.org/tmlr/papers/), we present a probabilistic (Bayesian) framework in which gradients are treated as latent variables and estimated gradients are observables. (1/n)