Albina Klepach

researching RL

[Albina Klepach @_cinemere]

🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:

How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?

Our new work, Object-Centric Latent Action Learning, tackles exactly this.

Thread ↓

[Albina Klepach @_cinemere]

If you are interested in diffusion, check out @konovalova7956 's new preprint!

[Nina Konovalova @konovalova7956]

New paper out! 🎉 SHIFT: Steering Hidden Intermediates in Flow Transformers — activation steering, but for DiT diffusion models.

https://t.co/hlRvg6Si3P

🧵 thread:

[Albina Klepach @_cinemere]

Check out a new ICLR paper from our lab

[Andrei Polubarov @earo050]

Is it possible to build a multi-domain action model capable of adapting to unseen dynamics?

Check out our new #ICLR2026 paper! We pushed in-context RL scaling further and released Vintix II.

👇👇👇

[Albina Klepach @_cinemere]

For those who haven’t seen our work on latent action models, here is a thread

[Albina Klepach @_cinemere]

🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:

How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?

Our new work, Object-Centric Latent Action Learning, tackles exactly this.

Thread ↓

[Albina Klepach @_cinemere]

Thanks to @RealAAAI for the conference. So many interesting new connections. Hope that now more people are aware of the beauty of latent actions for robotics 🤖

#AAAI2026 #robots #ai #aaai #Singapour

[Albina Klepach @_cinemere]

Don't forget to visit my oral or/and poster today on scalable imitation learning via object-centric pretraining.

Oral: Garnet 218 @ 9:50 am
Poster: Hall 4

Also, feel free to reach out if you want to chat about continual, imitation and/or reinforcement learning while at AAAI!

[Albina Klepach @_cinemere]

@AmitLeViAI Come across my paper on scalable imitation learning

[Albina Klepach @_cinemere]

🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:

How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?

Our new work, Object-Centric Latent Action Learning, tackles exactly this.

Thread ↓

[Albina Klepach @_cinemere]

🙏Thanks to my great co-authors! @how_uhh @suessmannn @vladkurenkov

And thanks to all for inspiring research on latent actions @jparkerholder @_rockt @svlevine @SeonghyeonYe @jang_yoel @furongh and on slot-attention @FrancescoLocat8 @tkipf @Dazitu_616

[Albina Klepach @_cinemere]

🤩Excited to share our #AAAI2026 Oral on #EmbodiedAI:

How can robots learn from noisy, unlabeled videos—like those on the internet—without action labels?

Our new work, Object-Centric Latent Action Learning, tackles exactly this.

Thread ↓

[Albina Klepach @_cinemere]

9/9 If you're at AAAI or interested in world models, imitation learning, or object-centric RL, check out our paper: https://t.co/A1HJN4coj4
Oral session: Jan 22, 9:30-10:00 Garnet 218
Poster session: Jan 22, Hall 4
Code (coming soon): https://t.co/bKLOS0tV4V

[Vladislav Kurenkov @vladkurenkov]

We released 87 hours of @LeRobotHF SO 100/101 datasets.

It is a unified, cleaned, and annotated repackage of 598 open-source community datasets (SO100 and SO101), totaling 22,709 episodes, ~9.4M frames, and 563 tasks.

[Denis Tarasov @ML_is_overhyped]

I’m asking for help. I was meant to start my PhD with @_rockt and @robertarail at UCL, but my UK background check was refused. My appeal seems unlikely to succeed, so I’m urgently searching for any PhD or research positions in academia or industry. Any help is appreciated.

[Vladislav Kurenkov @vladkurenkov]

🚀 Introducing cadrille: a new SOTA model for CAD reconstruction from images, point clouds, and text—all in one framework with the use of RLVR.

Multimodal inputs + RLVR = clean, editable 3D models.

🧵👇

[Denis Tarasov @ML_is_overhyped]

LLMs are amazing because they can learn in context — read, adapt, and act.

Can we do the same for reinforcement learning? That’s the promise of In-Context RL (ICRL).

But existing offline ICRL methods don’t even optimize rewards.

Our new paper shows why RL matters
🧵