Andrii Zadaianchuk 🇺🇦
@zadaianchuk.bsky.social
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
PhD in ETH Zürich and MPI IS, intern in Amazon AWS.
Structured representation learning for and by autonomous agents.
zadaianchuk.github.io
Pinned
go.bsky.app/5KXsVXb
Created Starter Pack for VISLab, if you see more people whom I should add suggest here
Created Starter Pack for VISLab, if you see more people whom I should add suggest here
Reposted by Andrii Zadaianchuk 🇺🇦
And the answer is 0.9999 for the win.
Lower confidence value always gives you worse results for more or less same runtime.
More in our RANSAC Tutorial at #ICCV2025
Lower confidence value always gives you worse results for more or less same runtime.
More in our RANSAC Tutorial at #ICCV2025
October 18, 2025 at 8:56 PM
And the answer is 0.9999 for the win.
Lower confidence value always gives you worse results for more or less same runtime.
More in our RANSAC Tutorial at #ICCV2025
Lower confidence value always gives you worse results for more or less same runtime.
More in our RANSAC Tutorial at #ICCV2025
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👇
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👇
August 14, 2025 at 6:52 PM
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👇
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!
I would say that the equivalent for humanoid robots would be to unwrap Chupa Chups Lollipop.
Take that Embodied AI!
September 19, 2025 at 10:32 PM
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!
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
September 13, 2025 at 3:32 PM
How to name your method: a comprehensive flow chart
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?
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?
August 11, 2025 at 2:11 PM
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?
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👇
Thread👇
July 24, 2025 at 4:26 PM
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👇
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 👇
simulatingrobotworlds.github.io
More info 👇
August 1, 2025 at 7:15 PM
Happy to organize #CoRL2025 Workshop! If you are interested in world models or learning simulators for robotics, consider joining!
simulatingrobotworlds.github.io
More info 👇
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.
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
August 1, 2025 at 6:11 PM
🚀 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.
The workshop aims to cover topics like physics-grounded simulation, photorealistic digital twins, AI-controlled simulators, to learned neural world models.
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
🗣️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
July 14, 2025 at 8:42 AM
🌍🤖 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
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
🧵
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
🧵
July 14, 2025 at 8:42 AM
🌍🤖 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
SENSEI learns to explore from humans by reusing semantics structure discovered by VLMs and exploring around most interesting for VLM states.
#ICML2025
Reposted by Andrii Zadaianchuk 🇺🇦
this post: ysymyth.github.io/The-Second-H...
The Second Half
tldr: We’re at AI’s halftime.
ysymyth.github.io
May 17, 2025 at 6:46 PM
this post: ysymyth.github.io/The-Second-H...
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
📬 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
April 14, 2025 at 11:04 AM
🚀 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
📬 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
arxiv.org/abs/2503.15200
O. Eberhard, M. Muehlebach, @claireve.bsky.social
March 20, 2025 at 11:05 AM
Interesting idea: RL with memory traces = exponential moving averages of latent encodings.
arxiv.org/abs/2503.15200
O. Eberhard, M. Muehlebach, @claireve.bsky.social
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/
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/
March 17, 2025 at 4:21 PM
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/
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/
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.
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.
March 8, 2025 at 6:30 PM
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.
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
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
March 2, 2025 at 11:04 AM
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
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 🇺🇦
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
February 20, 2025 at 2:50 PM
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.
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.
@GoogleAI internship deadline is Feb 28.
February 27, 2025 at 6:10 PM
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.
@GoogleAI internship deadline is Feb 28.
Reposted by Andrii Zadaianchuk 🇺🇦
computer vision researchers’ conversations with friends be like
February 26, 2025 at 8:51 PM
computer vision researchers’ conversations with friends be like
Who would be "Japan" to have an example?
February 25, 2025 at 9:28 AM
Who would be "Japan" to have an example?
Reposted by Andrii Zadaianchuk 🇺🇦
Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: shape-of-motion.github.io/results.html
Huge congrats to everyone involved and the community 🎉
Huge congrats to everyone involved and the community 🎉
February 24, 2025 at 6:52 PM
Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: shape-of-motion.github.io/results.html
Huge congrats to everyone involved and the community 🎉
Huge congrats to everyone involved and the community 🎉
Reposted by Andrii Zadaianchuk 🇺🇦
Elon Musk pusht die Pro-Kreml Parteien AfD und BSW im For You Feed von Twitter. Sie tauchen öfter im For You Feed auf als ihrem Anteil entspricht. Die Forscher haben dafür Test-Accounts erstellt, die allen Politikern auf X folgen. BSW und AfD waren krass überrepräsentiert.
February 19, 2025 at 10:02 AM
Elon Musk pusht die Pro-Kreml Parteien AfD und BSW im For You Feed von Twitter. Sie tauchen öfter im For You Feed auf als ihrem Anteil entspricht. Die Forscher haben dafür Test-Accounts erstellt, die allen Politikern auf X folgen. BSW und AfD waren krass überrepräsentiert.