It’s really excited to see the policy, trained entirely on simulation data, achieves robust zero-shot performance and outperforms teleoperators!
Reality of robotics: humanoid kung fu is solved before they can open doors with RGB. Here we are. Introducing the frontier of sim2real at NVIDIA GEAR. 100% sim data. RGB input only. Code name: 𝗗𝗼𝗼𝗿𝗠𝗮𝗻. We are opening the sim-to-real door. doorman-humanoid.github.io 🧵
I won’t be at #NeurIPS2025, but Jikai will be in San Diego presenting our HO-Cap poster on 12/3, 4:30–7:30pm. Stop by and talk to him about human data for robot manipulation!
Jikai Wang @JwRobotics (jwroboticsvision.github.io), who led our HO-Cap project, will be graduating next year. He’s looking for full-time roles in industry. If your team needs an expert in 3D hand-object interaction and robot simulation, please reach out to Jikai!
Recognizing unseen objects is a challenge our lab keeps working on. This dataset from Amazon looks exciting to explore! Our latest work @parker_sean_L @ruosenli @jingliqiang6 @JwRobotics combines few-shot object detection with LLMs for visual grounding irvlutd.github.io/MultiGrounding/
Announcing Kaputt: a large-scale dataset for visual defect detection in retail logistics with 238,421 images across 48,376 unique items – 40x as large as current benchmarks:
It's finally done, I've finished ripping out my full-body pipeline and replaced it with a hands-only version. Critical to make it work in a lot more scenarios! I've visualized the final predictions with @rerundotio! I want to emphasize that these are not the ground-truth values…
If you're not labeling your own data, you're NGMI. I take this seriously, so I finished building the first version of my hand-tracking annotation app using @rerundotio and @Gradio. The combination of Rerun's callback system and Gradio integration enables a highly customizable…
Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page: irvlutd.github.io/HOCap/
United States Tendencias
- 1. Cowboys 71.2K posts
- 2. LeBron 96.3K posts
- 3. Gibbs 19.2K posts
- 4. Lions 87.7K posts
- 5. Pickens 13.6K posts
- 6. #OnePride 10.1K posts
- 7. Brandon Aubrey 7,095 posts
- 8. #heatedrivalry 19.6K posts
- 9. Ferguson 10.5K posts
- 10. scott hunter 3,267 posts
- 11. #DALvsDET 6,105 posts
- 12. Eberflus 2,495 posts
- 13. CeeDee 10.3K posts
- 14. Shang Tsung 22.6K posts
- 15. Goff 8,457 posts
- 16. Bland 8,401 posts
- 17. DJ Reed N/A
- 18. fnaf 2 23.9K posts
- 19. Schotty 1,836 posts
- 20. Paramount 18.2K posts
Something went wrong.
Something went wrong.