Andrii Zadaianchuk 🇺🇦
@zadaianchuk.bsky.social
130 followers 150 following 63 posts
Postdoc UvA Amsterdam. PhD in ETH Zürich and MPI IS, intern in Amazon AWS. Structured representation learning for and by autonomous agents. zadaianchuk.github.io
Posts Media Videos Starter Packs
Pinned
go.bsky.app/5KXsVXb

Created Starter Pack for VISLab, if you see more people whom I should add suggest here
Reposted by Andrii Zadaianchuk 🇺🇦
Introducing DINOv3 🦕🦕🦕

A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale.
High quality dense features, combining unprecedented semantic and geometric scene understanding.

Three reasons why this matters👇
Reposted by Andrii Zadaianchuk 🇺🇦
The French often mention the roundabout at Arc de Triomphe as one of the ultimate tests for a self-driving vehicle.

I would say that the equivalent for humanoid robots would be to unwrap Chupa Chups Lollipop.

Take that Embodied AI!
Reposted by Andrii Zadaianchuk 🇺🇦
How to name your method: a comprehensive flow chart
I see, it is crazy that it is possible to be so consistent with such a type of memory!

I wonder if I would be walking for a "minute" (e.g. context size window) in the Genie 3, too far away from the main scene, would it start hallucinating much more than this?
I'm still puzzed by what type of memory would allow for such behavior:

The girl disappeared for several seconds after full occlusion (sec. 13-14), however appeared once more at the end of the video. So it is clearly not LSTM style memory.

Any ideas?
Reposted by Andrii Zadaianchuk 🇺🇦
SCMs often assume overly-dense causal graphs in dynamic settings 👉⚽🥎, since any object interaction is a potential causal edge, making them hard to scale. In joint work with @turanorujlu.bsky.social @cgumbsch.bsky.social & Martin Butz we propose a new Causal Process Model to tackle this.
Thread👇
Happy to organize #CoRL2025 Workshop! If you are interested in world models or learning simulators for robotics, consider joining!

simulatingrobotworlds.github.io

More info 👇
Reposted by Andrii Zadaianchuk 🇺🇦
🚀 We’re pleased to announce our workshop at CoRL 2025: Learning to Simulate Robot Worlds! Workshop website: simulatingrobotworlds.github.io
The workshop aims to cover topics like physics-grounded simulation, photorealistic digital twins, AI-controlled simulators, to learned neural world models.
Learning to Simulate Robot Worlds
Join the Learning to Simulate Robot Worlds workshop.
simulatingrobotworlds.github.io
Want to find out more about SENSEI?

🗣️ICML Poster West Exhibition Hall, 16 Jul, 11a.m. PDT, No. W-707
📜arxiv.org/abs/2503.01584
🌐sites.google.com/view/sensei-paper

Work done with @cgumbsch.bsky.social (co-first), @zadaianchuk.bsky.social, @pavelkolevbg.bsky.social and @gmartius.bsky.social

8/8
🌍🤖 What is the best way to explore the world to learn a robust world model from high dimensional data? 🤖🌍

SENSEI learns to explore from humans by reusing semantics structure discovered by VLMs and exploring around most interesting for VLM states.
#ICML2025
✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs.

With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk.

Accepted at ICML 2025🎉

Joint work with @cgumbsch.bsky.social
🧵
Reposted by Andrii Zadaianchuk 🇺🇦
🚀 Never miss a beat in science again!

📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner.

Check out our white paper: arxiv.org/abs/2504.08385
#OpenScience #AI #RecommenderSystems
Reposted by Andrii Zadaianchuk 🇺🇦
Interesting idea: RL with memory traces = exponential moving averages of latent encodings.

arxiv.org/abs/2503.15200

O. Eberhard, M. Muehlebach, @claireve.bsky.social
Reposted by Andrii Zadaianchuk 🇺🇦
Some hard evals.
1) IMC24 train -- Lizard. Reconstruction is good, but summer and winter are two separate nearby
2) IMC 24 train -- pond. Results are hard to tell.
3) Room with mirror - almost ideal
Overall the results are very impressive, but SfM is not solved yet.
1/
No, just to visualize proportions: e.g. %of public and % of private.
Do you have a map? This would be useful
Reposted by Andrii Zadaianchuk 🇺🇦
It is pointless, but.
My US friends - it will not stop after 4 years with next elections.
Either you stop it yourself in some way, or there will be no fair elections next time. Democracy is fragile.
P.S. If you like what is going on - enjoy.
u24.gov.ua

Best what one can do as individual is it set a monthly target and donate it until the victory automatically. For example as standing order from your bank using SEPA:

koloua.com/en/donate#sepa
Reposted by Andrii Zadaianchuk 🇺🇦
By popular demand, we are extending #ICCV2025 coverage to Bluesky. Stay tuned!
Reposted by Andrii Zadaianchuk 🇺🇦
Re-posting is appreciated: We have a fully funded PhD position in CMC lab @cmc-lab.bsky.social (at @tudresden_de). You can use forms.gle/qiAv5NZ871kv... to send your application and find more information. Deadline is April 30. Find more about CMC lab: cmclab.org and email me if you have questions.
forms.gle
Reposted by Andrii Zadaianchuk 🇺🇦
Our team @GoogleAI is hiring an intern. We are interested in having LMs understand and respond to users better. Topics include: teaching LMs to build “mental models” of users; improving LM's reasoning capability over long contexts.

@GoogleAI internship deadline is Feb 28.
Reposted by Andrii Zadaianchuk 🇺🇦
computer vision researchers’ conversations with friends be like