Isaac Tu retweeted
HUG won best paper at the Scaling H2R workshop #CoRL2026! I couldn't go but thanks @BillyYYan @Isaac1385 for repping 🏆
Thanks to the organizers @ruoshi_liu @KimD0ing @ryan_punamiya @JayLEE_0301 @SeonghyeonYe @jerthesquare_ @irmakkguzey @akashshrm02 and to @nvidia for the Thor!
Introducing Human Universal Grasping (HUG): dexterous grasping learned entirely from human hands, with zero robot data.
🌐 Website: grasping.io
📄 Paper: arxiv.org/abs/2606.17054
💻 Code: github.com/KevinyWu/hug
Loved being part of this project!
As we get closer to a world where we live among robots, it’s becoming more and more valuable for robots to learn quickly with and from people.
I’m very excited to share Steertuning, a novel approach that adapts robots to new tasks from 5 human demonstrations in under 5 minutes, from demonstration to deployment.
Website: steertuning.github.io/
Code: github.com/billy-yibo-yan/st…
Big things coming soon! We are getting better every release!
We pre-trained the same VLA on 100 hours of Human Archive’s OTS dataset and 100 hours of randomly sampled data from each of @microagi’s and @MeckaAI’s datasets on EgoVerse.
Overall, Human Archive data achieved the strongest results, with the highest overall task success rate. We observed particularly strong generalization to unseen objects.
Thread below 🧵👇
2
364
An early look at what our data does for downstream robot manipulation. More coming soon
We benchmarked only 7 hours of Human Archive data against 4 widely used public datasets totaling 17 hours: HOT3D, H2O, HOI4D, and TACO.
The results:
Human Archive only: 85% task success | 65.6% task progress
4 public datasets: 57.5% task success | 52.5% task progress
Mixture of all 5: 60% task success | 56.3% task progress
2
4
328
We benchmarked only 7 hours of Human Archive data against 4 widely used public datasets totaling 17 hours: HOT3D, H2O, HOI4D, and TACO.
The results:
Human Archive only: 85% task success | 65.6% task progress
4 public datasets: 57.5% task success | 52.5% task progress
Mixture of all 5: 60% task success | 56.3% task progress





