iiinova — where your digital self keeps evolving

Stannis Zhou

@stanniszhou.bsky.social

1.2K followers 219 following 7 posts

Research Scientist at Google DeepMind stanniszhou.github.io

Stannis Zhou @stanniszhou.bsky.social · 26/09/2025

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.

110

Reposted by Stannis Zhou

carldoersch.bsky.social @carldoersch.bsky.social · 09/04/2025

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

1259

Stannis Zhou @stanniszhou.bsky.social · 06/02/2025

Happy to share our new paper on better diffusions with scoring rules! Check it out at arxiv.org/abs/2502.02483

arxiv.org

Distributional Diffusion Models with Scoring Rules

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding r...

151

Reposted by Stannis Zhou

ruiqigao.bsky.social @ruiqigao.bsky.social · 02/12/2024

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.

625459

Stannis Zhou @stanniszhou.bsky.social · 23/11/2024

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

arxiv.org

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...

1483