Mandi Zhao
@ZhaoMandi
PhDing @Stanford, AI & robotics. Interning @MetaAI. Prev. @NVIDIAAI, @berkeley_ai
How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.
Probably the first and only public video from Skild AI: seeing Frankas, UR5s, humanoid arms - all bimanual robotiq 2f85 grippers?
At a robotics lab in Pittsburgh, engineers are building adaptable, AI-powered robots that could one day work where it's too dangerous for humans. The research drew a visit from President Trump, who touted U.S. dominance in AI as companies announced $90 billion in new investments.
I’m a big fan of this line of work from Columbia (also check out PhysTwin by @jiang_hanxiao: jianghanxiao.github.io/phystwin-web/) they really make real2sim work for the very challenging deformable objects, And show it’s useful for real robot manipulation. So far it seems a bit limited to…
Can we learn a 3D world model that predicts object dynamics directly from videos? Introducing Particle-Grid Neural Dynamics: a learning-based simulator for deformable objects that trains from real-world videos. Website: kywind.github.io/pgnd ArXiv: arxiv.org/abs/2506.15680…
Normally, changing robot policy behavior means changing its weights or relying on a goal-conditioned policy. What if there was another way? Check out DynaGuide, a novel policy steering approach that works on any pretrained diffusion policy. dynaguide.github.io 🧵
I'm giving a spotlight talk 10AM tomorrow, Room 213 at the agents-in-interactions workshop at #CVPR. Poster session is 11:45-12:15 at ExHall D #182-#201. Come say hi! Workshop schedule: agents-in-interactions.github.io
How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.
How can we move beyond static-arm lab setups and learn robot policies in our messy homes? We introduce HoMeR, an imitation learning agent for in-the-wild mobile manipulation. 🧵1/8
Single view reconstruction for cluttered scenes!
Imagine if robots could fill in the blanks in cluttered scenes. ✨ Enter RaySt3R: a single masked RGB-D image in, complete 3D out. It infers depth, object masks, and confidence for novel views, and merges the predictions into a single point cloud. rayst3r.github.io
thank you @Michael_J_Black ! The name DexMachina came from Deus ex machina (“god from the machine"): when a seemingly unsolvable problem is conveniently solved by an external force - like how our algorithm moves an object by itself before the policy gradually learns to take over
This wins for "best method name"! These are nice results and I'm happy that ARCTIC was useful. I believe that human demonstration is the path to rapid progress in dexterous, task-driven, manipulation.
Great work - Robot/object/contact co-tracking and curriculum via virtual object controllers are really good ideas. We will see similar ideas for humanoid whole-body manipulation and loco-manipulation very soon!
How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.