🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Here are the slides of my talk about learning on graphs with optimal transport at OTML Workshop NeurIPS Conference remi.flamary.com/pres/GW_OTML_2…

Here is a grid of different 1D optimal transport solutions for different regularizations (columns) and unbalanced marginal penalizations (rows). The example is coming to POT shortly and is done with a for loops because we now implement all those solvers in one function (ot.solve)

Gromov-Wasserstein distance is great, but what if its invariances were detrimental sometimes? Our AISTATS Conference paper (presented tonight) introduces Augmented GW which blends fine control over GW's invariances and guides its mapping with prior knowledge

Wouldn't it be great if we could merge the knowledge of 20 specialist models into a single one without losing performance? 💪🏻 Introducing our new ICML paper "Localizing Task Information for Improved Model Merging and Compression". 🎉 📜: arxiv.org/pdf/2405.07813 🧵1/9

If you are a student or academic researcher and want to make progress towards human-level AI: >>>DO NOT WORK ON LLMs<<< LLMs are an off ramp. Thousands of engineers are working on LLMs with enormous computing resources. The only way you could possibly contribute is by analyzing

Python Optimal Transport (POT) 0.9.4 released : works with numpy 2+, new quantized and low rank Gromov-Wasserstein solvers, and general unbalanced/regularized solvers in ot.solve. More details in 🧵1/7 github.com/PythonOT/POT/r…

Extremely happy to announce the (alpha) release 0.3.0 of SKADA Scikit Adaptation, a python toolbox for domain adaptation fully compatible with scikit-learn and PyTorch Code : github.com/scikit-adaptat… Doc: scikit-adaptation.github.io

Super proud to be part of this new open-source python library! Skada is set to transform domain adaptation, enabling robust learning across datasets with distribution shifts 🚀

Super happy to announce the release of TorchDR 0.1 : the Dimensionality Reduction (DR) library using PyTorch. Joint work with an amazing team : Rémi Flamary 🦋 , Mathurin Massias, Nicolas Courty, Cedric Vincent-Cuaz, Titouan Vayer, Aurélien Garivier. Thread 🧵. Repo : github.com/TorchDR/TorchDR

We are #hiring #PhD students via the #ELLIS PhD Program! Interested to work on (generative) #AI method development to advance personalized medicine? Located at the School of Computer Science and Life Sciences at EPFL🇨🇭and part of the EPFL_AI_Center, we are closely collaborating

Fine-tuning pre-trained models leads to catastrophic forgetting, gains on one task cause losses on others. These issues worsen in multi-task merging scenarios. Enter LiNeS 📈, a method to solve them with ease. 🔥 🌐: lines-merging.github.io 📜: arxiv.org/abs/2410.17146 🧵 1/11

Thank you for supporting my work 🙂🙏

Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community that acknowledges open source research software. Please continue to use, cite and contribute to POT ! Small🧵below for those interested