
Super excited to have been selected as a 2026 Google PhD Fellow for my work on flow-based language modeling! 🌊 Big thanks to my advisors @jwvdm and @wellingmax, everyone I've worked with, and @Google for the support! ❤️ blog.google/company-news/out…

PhD student in Geometric deep learning at @AMLabUvA with @erikjbekkers 🌟

Super excited to have been selected as a 2026 Google PhD Fellow for my work on flow-based language modeling! 🌊 Big thanks to my advisors @jwvdm and @wellingmax, everyone I've worked with, and @Google for the support! ❤️ blog.google/company-news/out…

Super cool work! 😍
Our survey on continuous diffusion and flow language models is out! ❤️ A little animated tour of what’s inside 👇 From representations and training to few-step generation, scaling, and open problems. continuous-lm.github.io

Our survey on continuous diffusion and flow language models is out! ❤️ A little animated tour of what’s inside 👇 From representations and training to few-step generation, scaling, and open problems. continuous-lm.github.io
New survey on Continuous Diffusion and Flow Language Models is out! 🌊💬 One of my first papers, back in early 2025, was on continuous simplex flows. After working on discrete diffusion, I wanted to try controllable sequence generation with flow matching, which naturally operates in continuous spaces. But at the time, I found them much harder to train well than discrete diffusion. 🥲 2026 has changed this picture completely! 🚀 It’s been super exciting to watch continuous LMs take off, but with the rapid advancements, it’s also becoming harder to keep up with all the new work across pre-training, few-step generation, guidance, and scaling 🥹 So together with @chandavidlee, @FEijkelboom, and @jw9730, we put together a survey that consolidates the continuous LM literature and its key insights into 37 pages. It covers everything from the early work before the so-called “winter” of continuous LMs to the wave of new papers in 2026 🌟 More in thread! 🧵

Joint work with @JCarrascoPollo @wellingmax @jwvdm @erikjbekkers @FEijkelboom Looking forward to presenting our work in Sydney! 🇦🇺

We introduce a new formulation of drifting models where the kernel's gradient directly determines the direction of motion. This provides theoretical guarantees and naturally extends the framework to data living on curved manifolds.

Excited to share that our paper, “Kernel-Gradient Drifting Models,” has been accepted to NeurIPS 2026! ❤️ 📄 Paper: arxiv.org/pdf/2605.10727v2 💻 Code: github.com/jcarrascopollo/kg…

🎉 Excited to share that RoVE was accepted as a spotlight at @TAGinDS! RoPE made attention scores position-aware but left the value pathway position-blind. RoVE fixes that with a parameter-free tweak, and it turns RoPE attention into an 𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐯𝐞 𝐜𝐨𝐧𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧🤘

🚨 🧵 New paper: Finite-particle rates for drifting models. Drifting trains 1-step generators by moving model μ toward data ν with a conservative or non-conservative velocity field. Consider data on x-axis, model on the y-axis. These 2 fields yield 2 different motions. 1/7

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


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