AlexC

PhD Student@Ecole Centrale 🇫🇷
📩 [email protected]

[AlexC @Beeg_Brain]

Thrilled to share that our paper “Object-Centric Representations Improve Policy Generalization in Robot Manipulation” was accepted to the Generalizable Prior Workshop at #CoRL 2025 🎉

We’ll be presenting our poster on, Sept 27 and I detail the paper below 👇

[Enactic @enactic_ai]

Stay tuned for the OpenArm 02 release.
GitHub: https://t.co/w4XCYRBHOo

[LeRobot @LeRobotHF]

The latest haptic glove from LeRobot's @nepyope looks alive 👀

Homunculus F³ drops next month.

Repost if you're hyped for new #lerobot hardware 🤗

#HF #lerobot #haptics

[LeRobot @LeRobotHF]

Releasing the Unfolding Robotics blog!

Time to unfold robotics: we trained a robot to fold clothes using 8 bimanual setups, 100+ hours of demonstrations, and 5k+ GPU hours.

Flashy robot demos are everywhere. But you rarely see the real story: the data, the failures, the engineering.

We’re sharing everything: code, data, and details in the blog → https://t.co/bZ8NXw0CZh

[AlexC @Beeg_Brain]

Very nice idea by @VilleKuosmanen, that's a cool read with morning coffee ☕️

[Ville🤖 @VilleKuosmanen]

Today’s robotics policies are prompted with language, even though robots struggle to connect directional words, like “left” or “roll clockwise”, into the corresponding motions.

We taught a diffusion policy to follow instructions directly in robot-native Motion Tokens

[AlexC @Beeg_Brain]

@huggingface I was preparing something around Lyon🇫🇷 I think this comes at a perfect timing !

[Robotics Papers @OWW]

STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation

Alexandre Chapin (LIRIS), Emmanuel Dellandréa (LIRIS), Liming Chen (LIRIS)
https://t.co/cGFaJdgUxR [𝚌𝚜.𝚁𝙾]

[Robotics Papers @OWW]

Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation

Alexandre Chapin (LIRIS), Bruno Machado (LIRIS), Emmanuel Dellandréa (LIRIS), Liming Chen (LIRIS)
https://t.co/xvSSDEW0vR [𝚌𝚜.𝚁𝙾]

[DailyPapers @HuggingPapers]

NVIDIA just released C-RADIOv4-H on Hugging Face

Combines SigLIP2, DINOv3 and SAM3
into a single vision foundation model

[AlexC @Beeg_Brain]

@RemiCadene Congrats and thank you for the amazing work on LeRobot, it has been a game changer for robotic accessibility ! 🙂 Good luck for your new projects, I'm sure something amazing will come out of it💪

[Dana Aubakirova @danaaubakir]

🏆 LIBERO VLA Leaderboard is live — the first-ever leaderboard for Vision-Language-Action models!
VLAs are growing fast, so we need efficient, fair evaluation on shared benchmarks and an open community space. Now it’s finally possible 👇

[AlexC @Beeg_Brain]

@_fracapuano @LeRobotHF Thanks I'll take a look at it 🫡

[AlexC @Beeg_Brain]

And this is just the beginning, we’re already working on the next version of the paper with expanded experiments and analysis. Stay tuned! 🚧📑 #lerobot #imitationlearning #robotics #benchmark #visionl

[AlexC @Beeg_Brain]

Thrilled to share that our paper “Object-Centric Representations Improve Policy Generalization in Robot Manipulation” was accepted to the Generalizable Prior Workshop at #CoRL 2025 🎉

We’ll be presenting our poster on, Sept 27 and I detail the paper below 👇

[AlexC @Beeg_Brain]

Would love to hear your thoughts!
👉 Do you see OCRs as the missing link for generalizable robot learning?
👉 Or are there other priors we should be exploring?
Excited to discuss at #CoRL! 🗣️