Tin Hadzi Veljkovic (@HvTin) profile picture

Intern @cusp_ai, PhD @UvA | Physics, Materials, Continuous Representations, etc etc etc.

Amsterdam
Joined July 2021
Photo by Tin Hadzi Veljkovic (@HvTin)Photo by Tin Hadzi Veljkovic (@HvTin)
Can a lightweight Transformer compete in crystal generation without equivariance? We show that it can. Crystalite combines chemistry-aware priors with geometric attention biases for: - SOTA CSP - best S.U.N. among all baselines - much faster sampling More info below! 👇
4
23
5
101
26,441
Tin Hadzi Veljkovic retweeted
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! 🧵
3
60
4
229
11,407
Tin Hadzi Veljkovic retweeted
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…
10
48
3
321
16,561
Tin Hadzi Veljkovic retweeted
(1/n) What if you could teach a vision model about 3D structure without a single 3D label and just a tiny fraction of its pretraining compute? 👁️ That’s 3DPoV. ✨ Heading to #ICML2026 in Seoul 🇰🇷 to share it 👇
1
12
1
29
3,616
Tin Hadzi Veljkovic retweeted
🌍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!
28
138
23
1,248
147,645
Tin Hadzi Veljkovic retweeted
Woo! #ICLR2026 Diffusion circle is happening tomorrow :D We’ll meet above the registration desk - can’t wait to meet everyone ❤️ ⌚️ Sat, Apr 25, 2:45 📍 Right above the registration desk and below the oral sessions
Who's at #ICLR2026 next week? I'm not (😢), which means someone else is going to have to organise a diffusion circle! I'm counting on you! Let me know, happy to amplify the announcement📢
1
11
53
6,183
I found this on the beach. I am scared. Does anyone know what this means? Thanks!
1
2
1
16
2,989
Tin Hadzi Veljkovic retweeted
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 :)
5
63
8
354
46,770
Tin Hadzi Veljkovic 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
Tin Hadzi Veljkovic retweeted
Sorted! @FEijkelboom and @GrigoryBartosh will be your #ICLR2026 diffusion circle organisers 🙏 stay tuned!
Who's at #ICLR2026 next week? I'm not (😢), which means someone else is going to have to organise a diffusion circle! I'm counting on you! Let me know, happy to amplify the announcement📢
1
10
3
52
11,697
Links here: 📄 Paper arxiv.org/abs/2604.02270v1 📝 Blogpost stases.github.io/blogposts/c… 💻 Code github.com/joshrosie/crystal… Feel free to reach out if this is interesting or relevant to your work!
1
9
878
Tin Hadzi Veljkovic retweeted
Discrete diffusion — but fast? ⚡️ Test-time inference — but for discrete data? 🧠 Categorical Flow Maps: continuous transport toward the simplex, turning discrete generation into a single-step problem. Built on Variational FM (CatFlow), we obtain (self-)distillation from scratch. Language, molecules, and test-time steering — one framework. Scaling to LLMs and foundation models next. Watch this space 👀
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_
2
19
2
104
21,624
Tin Hadzi Veljkovic retweeted
Flow Matching (FM) is one of the hottest ideas in generative AI - and it’s everywhere at #ICML2025. But what is it? And why is it so elegant? 🤔 This thread is an animated, intuitive intro into (Variational) Flow Matching - no dense math required. Let's dive in! 🧵👇
109
272
14
1,766
267,717
Tin Hadzi Veljkovic retweeted
We are very excited to announce that our workshop “#GRaM: Geometry-grounded Representation learning and generative Modeling” has been accepted to #ICML 2024. We invite papers on the following topics:
2
48
6
132
36,385
Tin Hadzi Veljkovic retweeted
Excited to share Rotating Features – accepted as oral at #NeurIPS2023 Rotating Features learn to represent object affiliation via their orientation on real-world data without labels. Let’s dive in! 📜 arxiv.org/abs/2306.00600 🖥️ github.com/loeweX/RotatingFe…
2
82
6
493
151,161
Tin Hadzi Veljkovic retweeted
Announcing Best Paper Awards for ML Reproducibility Challenge 2021! We had over 100+ submissions and we are happy to accept 43 reports in our main program. Congratulations to our best and outstanding paper award winners. See more here: paperswithcode.com/rc2021
3
27
10
99
Tin Hadzi Veljkovic retweeted
Allright! First lecture is done 🥳 I'll be filling up this YT playlist with more videos on *group equivariant deep learning* in the coming weeks. Regular g-convs: Done! Next up: Steerable g-convs! youtube.com/playlist?list=PL…
4
93
2
471