
Applied robotics research @ Disney Imagineering R&D, ex-@Google || physical AI, 3D printing
yes
Joined August 2008
- Tweets4K
- Following3.6K
- Followers877
- Likes11.3K
Pinned Tweet
Who said ancient technology has to remain ancient?
Thrilled to share that a project we've been secretly working on at @Disney Imagineering R&D has landed at Disney World!
Partnering expert stone carvers with robotic carving technology unlocks new creative opportunities!
1
2
291
Xavier Malina retweeted
What if three.js could render beyond the limits of the browser?
Meet ThreeRT: a native JS runtime and hardware-accelerated real-time path tracer, bringing lifelike lighting to Three.js scenes on macOS, Windows, iOS, Android, and Steam Deck.
Fully open source 🧵
This..is amazing. can't wait to play with it.
Googleが15m解像度の準グローバル標高モデルの実験版をGoogle Earth Engineのデータセットで公開している
CC BY 4.0ライセンスで使えるとのこと
Pléiades Neoや、WorldView、GeoEye、Pléiades、SPOTといった光学衛星のステレオ撮影画像から作成しているみたい
developers.google.com/earth-…
41
Xavier Malina retweeted
New blogpost: Fable-5.1 can hide secret messages in benign images.
We gave the image to another Fable in a fresh session and simply asked: "Is there a hidden message in this image?"
It recovered the exact message without being told how it was hidden.
Xavier Malina retweeted
Announcing the beta release of the Pi API. We’ve partnered with companies across diverse industries to adapt our models to their robots and applications, from harvesting strawberries to assembling servers. Now we’re opening access to more teams.
Xavier Malina retweeted
As robots become more reliable, DAgger becomes far less efficient.
eg 90% success means the person spends >90% of the time passively watching the robot
Key idea: failures come from similar initial states & we can focus learning on these states!
Paper: arxiv.org/abs/2610.05882
I've been thinking a lot about making robot learning scalable. To me, that means learning on the job, and using the human help still needed efficiently.
In Mulligan ⛳️, we focus each data-collection round on the initial states where the robot fails. This happens in deployment, with the robot doing the task and a person stepping in when needed.
On 3 real tasks and 2,550 blind evals, it improves on uniform collection at the same budget.
Xavier Malina retweeted
tested Jev as a real-time robotics policy in MuJoCo
it struggled at first, so i split each update into two calls: decide what to do next, then decide how to move the arm and gripper
Jev doesn’t accept images, it gets simplified geometry and contacts as text here
Awesome to hear @donttrythis and @iFixit discussing the misguided AB2047. We've got to stop this youtube.com/shorts/60N47ST4u…
Keep up the fight @David_Tobin
2
361
Xavier Malina retweeted
Here are the top models for each use case assuming they don’t get banned 😉
coding - backend - GPT 5.5
coding - frontend - Opus 4.8
chat - Gemini Flash 3.5
real-time - Grok 4.3
video - Seedance 2.0 / Imagine
image - GPT-Image 2
cheap coding - Kimi 2.7
small worker bee - Deepseek Flash
search / retrieval - GPT 5.4
multi tool loop - Sonnet 4.6
voice - Flash live
role play - Grok fast
Xavier Malina retweeted
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: darioamodei.com/post/policy-…
Original post on @LinkedIn :
linkedin.com/posts/walt-disn…
84
Xavier Malina retweeted
ISRU is critical for life off-world but it is also crucial for thriving here on Earth. Itemfarm builds machines that use the material around you to manufacture what you need.
In 2026 we're scaling so when humanity expands off world we'll be ready.
Creation is for everyone.
Papers like this are so critical for large format additive manufacturing to become more reliable research.nvidia.com/labs/sil…
What will we build with this hmmm
sam3.cpp - Meta's SAM 3 in pure C++ with @ggerganov's ggml
- Supports SAM 3.1, 3, 2.1, 2 and EdgeTAM
- FP16, 4-bit quant (EdgeTAM in 15 MB)
- Apple Metal GPU, CUDA, CPU
- Text-prompted: "peach" → every peach
- Single-file C++14
Performance-wise:
- 100ms object detection, segmentation
- Video object segmentation @ 20FPS on M4 Pro with EdgeTAM
github.com/PABannier/sam3.cp…
2
143
















