iiinova — where your digital self keeps evolving

Reposted by Andrii Zadaianchuk 🇺🇦

Akshay L Chandra @acl21.bsky.social · 05/05/2026

🚀 Announcing #RSS2026 workshop: Robot World Models 🌐🤖🐨🌐 July 17, 2026 in 🇦🇺! We're bringing together researchers building the next generation of WM for robots — models robots can act in: controllable, long-horizon & grounded in real dynamics. 🔗 robot-worldmodels.github.io

192

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 05/05/2026

Super exited to co-organize Robot World Model workshop in #RSS2026!

060

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 04/12/2025

I think kids at school should have a class on writing tests.

000

Reposted by Andrii Zadaianchuk 🇺🇦

Dmytro Mishkin @ducha-aiki.bsky.social · 18/10/2025

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

162

Reposted by Andrii Zadaianchuk 🇺🇦

Max Seitzer @maxseitzer.bsky.social · 14/08/2025

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👇

2269

Reposted by Andrii Zadaianchuk 🇺🇦

Andrei Bursuc @abursuc.bsky.social · 19/09/2025

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!

3181

Reposted by Andrii Zadaianchuk 🇺🇦

Christian Wolf @chriswolfvision.bsky.social · 13/09/2025

How to name your method: a comprehensive flow chart

14310

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 11/08/2025

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?

120

Reposted by Andrii Zadaianchuk 🇺🇦

Charley Wu @thecharleywu.bsky.social · 24/07/2025

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👇

arxiv.org

Reframing attention as a reinforcement learning problem for causal discovery

Formal frameworks of causality have operated largely parallel to modern trends in deep reinforcement learning (RL). However, there has been a revival of interest in formally grounding the representati...

0207

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 01/08/2025

Happy to organize #CoRL2025 Workshop! If you are interested in world models or learning simulators for robotics, consider joining! simulatingrobotworlds.github.io More info 👇

010

Reposted by Andrii Zadaianchuk 🇺🇦

Katherine Liu @katherineliu.bsky.social · 01/08/2025

🚀 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.

simulatingrobotworlds.github.io

Learning to Simulate Robot Worlds

Join the Learning to Simulate Robot Worlds workshop.

173

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 14/07/2025

🌍🤖 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

010

Reposted by Andrii Zadaianchuk 🇺🇦

Chris Paxton @cpaxton.bsky.social · 17/05/2025

this post: ysymyth.github.io/The-Second-H...

ysymyth.github.io

The Second Half

tldr: We’re at AI’s halftime.

051

Reposted by Andrii Zadaianchuk 🇺🇦

Andreas Geiger @andreasgeiger.bsky.social · 14/04/2025

🚀 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

19420

Reposted by Andrii Zadaianchuk 🇺🇦

Christian Wolf @chriswolfvision.bsky.social · 20/03/2025

Interesting idea: RL with memory traces = exponential moving averages of latent encodings. arxiv.org/abs/2503.15200 O. Eberhard, M. Muehlebach, @claireve.bsky.social

3475

Reposted by Andrii Zadaianchuk 🇺🇦

Dmytro Mishkin @ducha-aiki.bsky.social · 17/03/2025

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/

1125

Reposted by Andrii Zadaianchuk 🇺🇦

Dmytro Mishkin @ducha-aiki.bsky.social · 08/03/2025

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.

1567

Reposted by Andrii Zadaianchuk 🇺🇦

#ICCV2025 @iccv.bsky.social · 28/02/2025

By popular demand, we are extending #ICCV2025 coverage to Bluesky. Stay tuned!

0294

Reposted by Andrii Zadaianchuk 🇺🇦

Shervin Safavi @neuroprinciplist.bsky.social · 20/02/2025

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

37487

Reposted by Andrii Zadaianchuk 🇺🇦

Sjoerd van Steenkiste @svansteenkiste.bsky.social · 27/02/2025

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.

111

Reposted by Andrii Zadaianchuk 🇺🇦

Jia-Bin Huang @jbhuang0604.bsky.social · 26/02/2025

computer vision researchers’ conversations with friends be like

0282

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 25/02/2025

Who would be "Japan" to have an example?

100

Reposted by Andrii Zadaianchuk 🇺🇦

Angjoo Kanazawa @akanazawa.bsky.social · 24/02/2025

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 🎉

37417

Reposted by Andrii Zadaianchuk 🇺🇦

Philip Kreißel 🇪🇺🇺🇦 @pkreissel.eurosky.social · 19/02/2025

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.

AfD und BSW sind überrepräsentiert im For You Feed

441162563

Reposted by Andrii Zadaianchuk 🇺🇦

The Tennessee Holler @thetnholler.bsky.social · 19/02/2025

European Parliament member 👇🏽

8814661415408

Reposted by Andrii Zadaianchuk 🇺🇦

Wieland Brendel @wielandbrendel.bsky.social · 11/02/2025

🚀 We’re hiring! Join Bernhard Schölkopf & me at @ellisinsttue.bsky.social to push the frontier of #AI in education! We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation. 👉 forms.gle/sxvXbJhZSccr...

1914

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 09/02/2025

I'm curious to which category "making things with LLM/code-gen" falls. I would guess that it still feels that the Python script entirely generated LLM (e.g., R1) still feels satisfying as you can modify any aspect of it, even if you don't have to most of the time for simple tasks.

000

Reposted by Andrii Zadaianchuk 🇺🇦

Cees Snoek @cgmsnoek.bsky.social · 03/02/2025

✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n 👇👇👇 @ellisamsterdam.bsky.social

1174

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 31/01/2025

Also as I may have VISA problems once more I want to apply as early as possible, do you know whom I should contact for an early invitation letter?

000

Reposted by Andrii Zadaianchuk 🇺🇦

Juliette Marrie @jlt-m.bsky.social · 31/01/2025

(1/3) Happy to share LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes, that uplifts visual features from models such as DINOv2 (left) & CLIP (mid) to 3DGS scenes. Joint work w. @dlarlus.bsky.social @jmairal.bsky.social Webpage & code: juliettemarrie.github.io/ludvig

16516

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 31/01/2025

Asking for a friend: how many hours it is OK to spend trying to fit answers including references to 1-page CVPR rebuttal answer and do not feel like I'm spending public money for something really useless?

000

Reposted by Andrii Zadaianchuk 🇺🇦

Andrei Bursuc @abursuc.bsky.social · 22/01/2025

Receiving #ICLR2025 decisions and then #CVPR2025 reviews shortly after

0275

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 08/01/2025

Useful thread to remind ourselves that while evidence can look like supporting opposite strong priors, in reality, evidence can suggest that both priors are incorrect and more evidence needed. P.S. 3 figures from the thread could be a nice triptych that would be a good reminder to stay open-minded.

020

Reposted by Andrii Zadaianchuk 🇺🇦

Andreas Geiger @andreasgeiger.bsky.social · 08/01/2025

I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.

313113

Reposted by Andrii Zadaianchuk 🇺🇦

Johannes Aalto @ajohannes.bsky.social · 20/12/2024

After reading about Genesis, I think quite a few features seem to come directly from Taichi ("parallel programming language for high-performance numerical computation") that uses pytorch backend. With all the marketing here, I'm most puzzled I haven't heard about Taichi before

182

Reposted by Andrii Zadaianchuk 🇺🇦

Sjoerd van Steenkiste @svansteenkiste.bsky.social · 12/12/2024

Neural Assets poster is happening now. Join us at East Exhibit Hall A-C #1507

031

Reposted by Andrii Zadaianchuk 🇺🇦

Luca Eyring @lucaeyring.bsky.social · 11/12/2024

Can we enhance the performance of T2I models without any fine-tuning? We show that with our ReNO, Reward-based Noise Optimization, one-step models consistently surpass the performance of all current open-source Text-to-Image models within the computational budget of 20-50 sec! #NeurIPS2024

1277

Reposted by Andrii Zadaianchuk 🇺🇦

locatelf.bsky.social @locatelf.bsky.social · 11/12/2024

Today I’ll be presenting the poster #5110 from Dingling Yao applying CRL to climate and dynamical systems identification “Marrying Causal Representation Learning with Dynamical Systems for Science” West Ballroom A-D, starting at 16:30 Come check it out!

072

Reposted by Andrii Zadaianchuk 🇺🇦

Chris Offner @chrisoffner3d.bsky.social · 10/12/2024

My earlier post was not intended to dunk on the Sora model or on Jim Fan, but to call out, and advise against, the ML community's frequent vice of resorting to "wishful mnemonics" – such as calling a video generation model a "physics engine". x.com/chrisoffner3...

2272

Reposted by Andrii Zadaianchuk 🇺🇦

Kristina Ulicna @kristinaulicna.bsky.social · 25/11/2024

Exciting opportunity to intern with me 🙋‍♀️ & the entire research unit lead by @jhartford.bsky.social 🧠 on single-cell representation challenges 🦠 in gene perturbation imaging data 🧬 Come join Valence Labs London office 🇬🇧 powered by @recursionpharma.bsky.social: job-boards.greenhouse.io/valencelabs/...

13015

Reposted by Andrii Zadaianchuk 🇺🇦

Yuki M Asano @yukimasano.bsky.social · 26/11/2024

LoRA et al. enable personalised model generation and serving, which is crucial as finetuned models still outperform general ones in many tasks. However, serving a base model with many LoRAs is very inefficient! Now, there's a better way: enter Prompt Generation Networks, presented today #BMVC

1325

Reposted by Andrii Zadaianchuk 🇺🇦

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 07/12/2024

go.bsky.app/5KXsVXb Created Starter Pack for VISLab, if you see more people whom I should add suggest here

043

Reposted by Andrii Zadaianchuk 🇺🇦

Jia-Bin Huang @jbhuang0604.bsky.social · 26/11/2024

Introducing Generative Omnimatte: A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections). It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.

313420

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 05/12/2024

Am I the only one who is thinking that one list of followers is an outdated way to decide what should be in the timeline? Why not multiple lists?

110

Andrii Zadaianchuk 🇺🇦 @zadaianchuk.bsky.social · 05/12/2024

I think such location+topic based lists are really useful! Found a lot of people with whom I was previously connected!

010