Albina Klepach @_cinemere

researching RL cinemere.github.io Joined July 2024

Tweets

25
Followers

69
Following

223
Likes

171

Albina Klepach @_cinemere

3 months ago

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

Nina Konovalova @konovalova7956

3 months ago

New paper out! 🎉 SHIFT: Steering Hidden Intermediates in Flow Transformers — activation steering, but for DiT diffusion models. arxiv.org/abs/2604.09213 🧵 thread:

1 2 6 191 1

0 0 1 92 0

View Details

Albina Klepach @_cinemere

3 months ago

Check out a new ICLR paper from our lab

Andrei Polubarov @earo050

3 months ago

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. 👇👇👇

1 6 16 1K 1

0 0 5 101 0

View Details

Albina Klepach @_cinemere

5 months ago

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

🤩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 ↓

1 6 22 2K 2

0 1 5 215 0

View Details

Albina Klepach @_cinemere

5 months ago

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

2 5 52 3K 3

View Details

Albina Klepach @_cinemere

5 months ago

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!

0 2 8 254 1

View Details

Albina Klepach @_cinemere

5 months ago

@AmitLeViAI Come across my paper on scalable imitation learning

Albina Klepach @_cinemere

5 months ago

1 6 22 2K 2

0 0 2 73 0

View Details

Albina Klepach @_cinemere

5 months ago

🙏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

0 0 8 123 0

View Details

Albina Klepach @_cinemere

5 months ago

9/9 If you're at AAAI or interested in world models, imitation learning, or object-centric RL, check out our paper: arxiv.org/abs/2502.09680 Oral session: Jan 22, 9:30-10:00 Garnet 218 Poster session: Jan 22, Hall 4 Code (coming soon): github.com/dunnolab/objec…

1 1 2 86 0

View Details

Albina Klepach @_cinemere

5 months ago

1 6 22 2K 2

View Details

Vladislav Kurenkov @vladkurenkov

7 months ago

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.

2 6 35 2K 8

View Details

Denis Tarasov @ML_is_overhyped

9 months ago

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.

14 34 248 41K 55

View Details

Vladislav Kurenkov @vladkurenkov

a year ago

🚀 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. 🧵👇

1 8 20 3K 8

View Details

Denis Tarasov @ML_is_overhyped

a year ago

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 🧵