iiinova — where your digital self keeps evolving

Stefan Baumann @stefanabaumann.bsky.social · 13/04/2026

We also release OWM, a benchmark for open-world sparse motion prediction in in-the-wild scenes. You only ever observe one future, but the model should capture all plausible ones -- evaluating that properly needed a new benchmark.

110

Stefan Baumann @stefanabaumann.bsky.social · 13/04/2026

Where this gets fun: billiard shot planning. Sample thousands of "what if I strike it this way?" rollouts, pick the best one, execute. Same training data, same compute budget. Myriad sinks the shot 78% of the time. Best video model: 16%. You can plan well when you can actually explore enough futures

110

Stefan Baumann @stefanabaumann.bsky.social · 13/04/2026

Why? 2,200 samples/min on one GPU vs. ~0.05-0.7 for video models. On our open-world motion benchmark, Myriad (665M params) matches or beats models with 4.5-14B params in accuracy. Match the compute budget between models, and the gap becomes massive.

110

Stefan Baumann @stefanabaumann.bsky.social · 13/04/2026

From an image, we predict point trajectories with an efficient model -- one timestep at a time, like mentally unrolling a chain of interactions. No frames. No rendering. Just dynamics. This avoids the "visual tax": the enormous cost video models pay to generate every pixel to reason about motion.

120

Stefan Baumann @stefanabaumann.bsky.social · 13/04/2026

You don't imagine the future by mentally rendering a movie. You trace how things move -- abstractly, sparsely, step by step. We built a model that does exactly this. It predicts motion, not pixels -- and it's 3,000× faster than video world models. Myriad, accepted at @cvprconference.bsky.social

2259

Stefan Baumann @stefanabaumann.bsky.social · 13/03/2026

I don't know what your colleague did, but you can do significantly better than 0.0013 if you use assistance. All of these samples still had at least a distance of 1 in 255^3 color

010

Stefan Baumann @stefanabaumann.bsky.social · 13/03/2026

As Eric already said, primarily a matter of screen quality and ambient vs screen brightness - I would not consider myself to have extraordinarily good color perception, just a bright, good screen in a dark room. Super fun though!

130

Stefan Baumann @stefanabaumann.bsky.social · 15/10/2025

⚡️ FPT generalizes from open-set training. Applications: • Articulated motion (Drag-A-Move): fine-tuned FPT outperforms specialized models for motion prediction • Face motion: zero-shot, beats specialized baselines • Moving part segmentation: emerges from formulation

120

Stefan Baumann @stefanabaumann.bsky.social · 15/10/2025

⚙️ Unlike other methods, we don't regress or sample one trajectory. FPT 𝘳𝘦𝘱𝘳𝘦𝘴𝘦𝘯𝘵𝘴 𝘵𝘩𝘦 𝘧𝘶𝘭𝘭 𝘮𝘰𝘵𝘪𝘰𝘯 𝘥𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘪𝘰𝘯, enabling: • interpretable uncertainty • controllable interaction effects • efficient prediction (>100k predictions/s)

130

Stefan Baumann @stefanabaumann.bsky.social · 15/10/2025

💡 Our idea: Predict 𝗱𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻𝘀 of motion, not just one flow field instance. Given a few pokes, our model outputs the probability 𝘥𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘪𝘰𝘯 of how parts of the scene might move. → This directly captures 𝘶𝘯𝘤𝘦𝘳𝘵𝘢𝘪𝘯𝘵𝘺 and interactions.

130

Stefan Baumann @stefanabaumann.bsky.social · 15/10/2025

🧠 Understanding how the world 𝘤𝘰𝘶𝘭𝘥 change is core to physical intelligence. But most models predict 𝗼𝗻𝗲 𝗳𝘂𝘁𝘂𝗿𝗲, a single deterministic motion. The reality is 𝘶𝘯𝘤𝘦𝘳𝘵𝘢𝘪𝘯 and 𝘮𝘶𝘭𝘵𝘪-𝘮𝘰𝘥𝘢𝘭: one poke can lead to many outcomes.

120

Stefan Baumann @stefanabaumann.bsky.social · 15/10/2025

🤔 What happens when you poke a scene — and your model has to predict how the world moves in response? We built the Flow Poke Transformer (FPT) to model multi-modal scene dynamics from sparse interactions. It learns to predict the 𝘥𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘪𝘰𝘯 of motion itself 🧵👇

1248

Stefan Baumann @stefanabaumann.bsky.social · 26/07/2025

tl;dr: do importance weighting/sampling on a sequence level, not a token level. Makes everything behave much better (see below) and makes more sense from a theoretical perspective, too. Paper: www.arxiv.org/abs/2507.18071

030

Stefan Baumann @stefanabaumann.bsky.social · 26/07/2025

I'm calling it now, GSPO will be the next big hype in LLM RL algos after GRPO. It makes so much more sense intuitively to work on a sequence rather than on a token level when our rewards are on a sequence level.

140

Stefan Baumann @stefanabaumann.bsky.social · 25/07/2025

Absolutely 100% this. Who would want to read papers like VGG-T

130

Stefan Baumann @stefanabaumann.bsky.social · 14/02/2025

What a PhD, fantastic work! Two incredible banger papers already, and now this one. And all that in actually three years. Really looking forward to what you'll be up to next!

110