Stannis Zhou
@stanniszhou.bsky.social
Research Scientist at Google DeepMind
stanniszhou.github.io
stanniszhou.github.io
Thrilled to share the launch of Gemini Robotics 1.5! This is a major step for generalist robots, thanks to a new motion transfer mechanism allowing zero-shot skill transfer between embodiments. I’m incredibly proud of our team's key contributions to this effort—a project I was honored to co-lead.
September 26, 2025 at 3:01 PM
Thrilled to share the launch of Gemini Robotics 1.5! This is a major step for generalist robots, thanks to a new motion transfer mechanism allowing zero-shot skill transfer between embodiments. I’m incredibly proud of our team's key contributions to this effort—a project I was honored to co-lead.
Reposted by Stannis Zhou
We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io
April 9, 2025 at 2:04 PM
We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io
Happy to share our new paper on better diffusions with scoring rules!
Check it out at arxiv.org/abs/2502.02483
Check it out at arxiv.org/abs/2502.02483
February 6, 2025 at 5:24 AM
Happy to share our new paper on better diffusions with scoring rules!
Check it out at arxiv.org/abs/2502.02483
Check it out at arxiv.org/abs/2502.02483
Reposted by Stannis Zhou
A common question nowadays: Which is better, diffusion or flow matching? 🤔
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
December 2, 2024 at 6:45 PM
A common question nowadays: Which is better, diffusion or flow matching? 🤔
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Hello world! Excited to (re)share from X our new paper on "Diffusion Model Predictive Control" (D-MPC). Key idea: leverage diffusion models to learn a trajectory-level (not just single-step) world model to mitigate compounding errors when doing rollouts. arxiv.org/abs/2410.05364 🧵 1/4
Diffusion Model Predictive Control
We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns a multi-step action proposal and a multi-step dynamics model, both using diffusion models, and combines them for...
arxiv.org
November 23, 2024 at 4:33 AM
Hello world! Excited to (re)share from X our new paper on "Diffusion Model Predictive Control" (D-MPC). Key idea: leverage diffusion models to learn a trajectory-level (not just single-step) world model to mitigate compounding errors when doing rollouts. arxiv.org/abs/2410.05364 🧵 1/4