Jorge Carrasco

Excited to share our new paper: Kernel-Gradient Drifting Models! 🧲 We reformulate Drifting Models through the lens of kernel gradients, yielding strong theoretical guarantees, non-Euclidean generalization, and improved performance. Very lucky to work with such an amazing team ❤️

Work done with the amazing team of  @JCarrascoPollo , @wellingmax @jwvdm @erikjbekkers @FEijkelboom❤️ Thanks for making this possible!

3. Improved performance across a range of tasks 📈

2. Natural generalization to non-Euclidean geometries, and discrete data generation by working on the probability simplex 🌎

Why is this useful? This new reformulation gives us: 1. Strong theoretical guarantees, including a score-matching interpretation of the drifting dynamics for a broad class of kernels, as well as a Wasserstein gradient flow interpretation of the optimization 🧲

🏎️Drift in the right direction🏎️ Introducing kernel-gradient drifting models: a reformulation of drifting models where the kernel itself defines the direction of motion through its gradient. 📜Paper: arxiv.org/pdf/2605.10727 💾Notebook: tinyurl.com/mv2jhuky

Ali did some amazing work on the hottest new generative model: drifting models (from Mingyang Deng @Goodeat258 et al., out of Kaiming He's group). Speeds up training a lot using low rank Nyström approximation. Check out Ali's full thread. Paper and code available!

Flow-LLM Blogpost :D flow-based-llms.github.io In the last few weeks, a bunch of work on flows for language came out 🌊 That is exciting, because it makes truly parallel text generation feel real: generation where models can keep refining the whole response during inference, instead of committing token by token. I wrote an intuitive and animated introduction to the area — why autoregression has a structural ceiling, why discrete diffusion only partly escapes it, and why flows may be the first genuinely parallel alternative. Here's an overview of the key parts of the blog - and let's chat at #ICLR2026 :)

@FEijkelboom @olgazaghen @nblqbl @HvTin @GrigoryBartosh @maxxxzdn We also have 15 papers presented at various workshops, see the poster for details

🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu)! We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include: 📺 Videos: Step-by-step derivations. 📝 Notes: Mathematically self-contained lecture notes 💻 Coding: Hands-on exercises for every component We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models. Everything is available here: diffusion.csail.mit.edu A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints! #MachineLearning #GenerativeAI #MIT #DiffusionModels #AI

We’ve released the code for Drifting Models :) Includes full training, inference, and pretrained weights. Curious to see what people build on top of this. github.com/lambertae/drif…

[1/D] 🤔 What are drifting models really connected to? 📢 Our new paper, A Unified View of Drifting and Score-Based Models, shows that the bridge to score-based models is clear and precise (w/ team and @mittu1204, @StefanoErmon, @MoleiTaoMath)! ✍️ Main takeaway: drifting is more closely connected to score-based (diffusion) modeling than it may first appear! 🔗 arxiv.org/abs/2603.07514 🎯 Here’s why: Drifting’s mean-shift moves a sample toward the kernel-weighted average of nearby samples. Score function points toward regions of higher density. So both describe local directions that push samples toward where data is denser. We show that this link is exact for Gaussian kernels (Section 4.1): 📌drifting’s mean-shift = a rescaled score-matching field between the Gaussian-smoothed data and model distributions — the vector field underlying score matching (Tweedie!). 📌This also clarifies the bridge to Distribution Matching Distillation (DMD): both use score-based transport directions, but only differ in how the score is realized—drifting does so nonparametrically through kernel neighborhoods, whereas DMD relies on a pretrained diffusion teacher. 🤔 So what happens for the default Laplace kernel used in drifting models? Let’s look below 👇

New paper accepted at @GRaM_org_ !!! 🥳🤩 Here is a small infomercial about it 🤠 If you are interested, you can find extra info in the next tweet 👇

The "drifting model" is not just a new generative model, but also opens a new direction for representation learning! In this blog, I discussed how the drifting model could elegantly fix the failure modes of VQ-VAE and propose a "Drifting VQ-VAE". kindxiaoming.github.io/blog/2026/repr…

📍Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization Spotlight paper at TAGinDS!!!! More info 👇

You like discrete diffusion, but it's too slow? 🥀 You like test-time inference, but it's for continuous methods? 😩 We fixed it. Introducing Categorical Flow Maps: continuously sample discrete data in a single step 🚀💫 How? 🧵⬇️ 💪 Co-led with @FEijkelboom, @daan_roos_