UvA AMLab (@AmlabUva) header
UvA AMLab (@AmlabUva) profile picture

The official account of the Amsterdam Machine Learning Lab (AMLab) @UvA_Amsterdam, co-directed by Max Welling (@wellingmax) and Jan-Willem van de Meent (@jwvdm)

Amsterdam, Netherlands
Joined October 2020
Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)Photo by UvA AMLab (@AmlabUva)
We are happy to introduce Mosaic, a fast and accurate weather forecasting model that is capable of capturing extreme events. See the thread for details.
🌍Today we release Mosaic, a probabilistic weather model that shifts the Pareto frontier of ML weather forecasting. It matches the skill of state-of-the-art models while generating a 24-member, 10-day global forecast in under 12 s on a single H100. Thread!
1
6
1,894
UvA AMLab retweeted
Excited to be at #ICLR2026 in Rio this week! Presenting “Soft Tokens, Hard Truths” Saturday 10.30am (Pavilion 3, P3-#1020). Feel free to DM me to chat about self-improvement, reasoning, code gen. I’m also on the job market for industry research positions.
🔥New preprint: Soft Tokens, Hard Truths Introduces the first scalable continuous-token RL method for LLMs - no reference CoTs needed; scales to hundreds of thought tokens. Best to train soft, infer hard! Pass@1 parity ⚖️, Pass@32 gains 📈& better robustness 🛡️ vs. hard CoT 1/🧵
6
22
3,641
UvA AMLab retweeted
I am going to be at ICLR 🇧🇷 this week! 🥳 Would love to grab a coffee and chat about - agentic search for scientific discovery, - weather forecasting, or - AI for large scale scientific problems. I will also present three papers:
3
9
1
64
6,323
UvA AMLab retweeted
Excited to be in Brazil very soon to attend ICLR 😎 Hmu if you want to grab coffee ☕️ and/or chat about generative models for geometric/structured data, AI4science, or free step - THE Brazilian rave dance 🔥🇧🇷
1
3
35
2,003
Heading to ICLR in Brazil 🇧🇷 :D Hmu if you want to chat about (variational) flow matching, discrete distillation, and flow-based language models :D
3
4
1
60
5,141
UvA AMLab retweeted
✨Excited to share that our work “MSPT: Multi-Scale Patch Transformer for Efficient Large-Scale Physical Modeling” was selected as a #CVPR2026 Highlight! 📰 Paper: arxiv.org/abs/2512.01738 🤗 Project page: pedrocurvo.com/projects/mspt 💻 Code: github.com/pedrocurvo/mspt 🏆State-of-the-art performance on PDE benchmarks (elasticity, fluids, porous flow) and large-scale CFD tasks like ShapeNet-Car. --- Scaling neural PDE solvers to millions of spatial elements requires capturing two things at once: 1⃣ fine-grained local interactions: stress concentrations, small-scale turbulence, sharp gradients; 2⃣ long-range global dependencies: pressure coupling in fluids, far-field boundary conditions in aerodynamics; Current methods tend to trade one for the other: local attention preserves detail but misses global structure, while global aggregation (e.g., fixed-size slices) captures the big picture but oversmooths fine scales. MSPT uses Parallelized Multi-Scale Attention (PMSA) to capture local and global interactions within a single, efficient attention call. Key highlights: 📈Near-linear scaling to millions of points on a single GPU 🔎Unified local-global modeling: fine-grained interactions within patches + global context through shared supernodes. 🚀 Fast and expressive: pushes the Pareto frontier on PDE modelling. 🌳Flexible across geometries: supports arbitrary meshes and point clouds via ball-tree partitioning. Congrats to @pmpcurvo who pulled it off, co-supervised with @jwvdm.
25
2
142
8,168
Excited to share that we're looking for a new colleague at @AMLab_UvA : Assistant Professor in AI for Science 🔬🤖 AMLab is a world-class ML research group embedded in Amsterdam's thriving AI ecosystem: leading research groups, an ELLIS unit, startups, and big tech — all within reach. And Dutch academic labor conditions are genuinely among the best in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancie…
2
36
7
202
33,430
We also have 15 papers presented at various workshops, see the poster for details
6
12
542
📢 GRaM workshop is back!! This time at #ICLR2026 🌟Excited to be in Brazil 🇧🇷! More information coming soon! @iclr_conf @GRaM_org_
5
3
15
7,695
Happening now at #NeurIPS2025! Poster #3904
Presenting today at @NeurIPSConf from 11am-2pm (poster number #3904)👇👇
1
1,171