Yutong Wang

[Yutong Wang @w13659760]

Manipulation is harder when the robot flies. 🚁

Moving the arm can shift the drone, and wind can push it off course. The policy and controller have to work together.

Here's AM-Bench: A Simulation Suite and Benchmark for Aerial Manipulation
https://t.co/O8uRFIITtB

#CoRL2026

[Xiaoxuan Ma @XiaoxuanMa_]

🥳Introducing SNAP3D — physically compatible 3D part generation from a single image.

Existing methods can generate visually appealing 3D parts, but the generated parts are often not physically compatible for assembly.

With SNAP3D, the parts are designed to fit together in the real world.

No glue. No screws. Just print, snap, and build!

🖨️ Try it with your 3D printer!

🔗 Project page: https://t.co/p9Y4SZrvjp
💻 Code: https://t.co/DvRQtUzsbp
🎬 Full video: https://t.co/GRfPjCKx8f

[Yutong Wang @w13659760]

7/7 Ready to take robot manipulation airborne? 🚁

🌐 Website: https://t.co/O8uRFIITtB
💻 Code: https://t.co/Lz8TKiAhAo
📄 Paper: https://t.co/7TgKjpNAD5

Built with @LeCARLab, @AirLabCMU & ARI Lab. We'd love to see what you build! 🙌

[Yutong Wang @w13659760]

Manipulation is harder when the robot flies. 🚁

Moving the arm can shift the drone, and wind can push it off course. The policy and controller have to work together.

Here's AM-Bench: A Simulation Suite and Benchmark for Aerial Manipulation
https://t.co/O8uRFIITtB

#CoRL2026

[Yutong Wang @w13659760]

6/7 How far can today's robot policies go in flight? 🤖

We benchmark ACT, Diffusion Policy & VLAs, then study fine-tuning, action interfaces & embodiments.

[Angchen Xie @AngchenXie]

Humanoid robots often fail when conditions change.

A heavy backpack. A soft floor. A steep slope. Suddenly, the same controller may not work.

Meet FADA.
🦾

It adapts a humanoid to new conditions using only its own experience, keeping what the robot wants to do and changing only how it does it.

About two minutes. No rewards. No demonstrations. No simulator retuning.

🧵