Jason Kim

SLAM guy like me feel miserable when I see posts like this. Just hoping that resource limited systems with no communication or GPS still needs SLAM and state estimation, especially for legged robots.

VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences Kai Deng, Zexin Ti, Jiawei Xu, Jian Yang, Jin Xie tl;dr: sequence->overlapping chunks->alignment and loop closure with confidence kind of same with large-scale GS ORB-SLAM2 is…

Optimization-based ones might have hit their upper limit, but the task isn’t solved. Since DUSt3R, Learning-based ones are starting to catch up and even surpass in cases like sparse views, textureless scenes—yet still lag in areas where traditional methods excel, e.g. large-scale

Registration beyond Points: General Affine Subspace Alignment via Geodesic Distance on Grassmann Manifold Jaeho Shin, Hyeonjae Gil, Junwoo Jang, @GhaffariMaani, @_ayoungk tl;dr: optimal cost function with geodesic distance on Grassmann manifold for line-plane registration…

View with its side shut. I’m kinda finding its potential for humanoid extension right after this kid starts walking

Are current eval/deployment practices enough for today’s robot policies? Announcing the Eval&Deploy workshop at CoRL 2025 @corl_conf, where we'll explore eval + deployment in the robot learning lifecycle and how to improve it! eval-deploy.github.io 🗓️ Submissions due Aug 30

Unitree Introducing | Unitree R1 Intelligent Companion Price from $5900 Join us to develop/customize, ultra-lightweight at approximately 25kg, integrated with a Large Multimodal Model for voice and images, let's accelerate the advent of the agent era!🥰

[IEEE RAL'25 & IROS'25] UA-MPC: Uncertainty-Aware Model Predictive Control for Motorized LiDAR Odometry github.com/kafeiyin00/UA-…

SLAM remains one of the most important problems in robotics. Yuheng worked on "MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry" which was the ICRA 2025 best paper. And has open source code for visual odometry!

It’s now all about Lie group… but it still gives me a belief that there are still more things to do on manifolds

焼き土下座 Policy

today we are doing sim2real

We make sure they don’t run away

Excited that our work, Concept Attention, was selected as an Oral Presentation at ICML 2025 and recently won the Best Paper Award at the CVPR Workshop on Visual Concepts. Concept Attention allows you to visualize the presence of text concepts in generated videos and images.

What are robot world models? If you follow the robotics space, you'll have almost certainly heard the term "world model." In the end, these mean using generative ai to build data-driven simulators or planners in order to build general-purpose robots. In this post I write about…

👀

What a BEAST

📄 arxiv.org/abs/2506.05282 💻 github.com/GradientSpaces… 🤹 w/ Tao Sun, @liyuan_zz, @ShengyHuang, @SongShuran