The authors assembled more than 20,000 hours of processed robot demonstrations, UMI recordings, egocentric human demonstrations and human-to-robot converted data.
Predictive visual models improve action generation for generalist robot manipulation
InternW0-Delta combines video, semantic, geometric and action models, trained on more than 20,000 hours of heterogeneous demonstrations.
Chinese Tech
Xingyu Miao · Zizun Li · Baole Fang · Kaiwen Song · Tenghui Wang · Hanxue Zhang · +42 more
Shanghai AI Laboratory
Research Digest··2 min read
The authors built a world action model that uses pretrained visual dynamics and geometric knowledge to generate robot actions without rolling out future video during deployment.
Why this paper
From Shanghai AI Laboratory
In one line
InternW0-Δ jointly models visual dynamics and action generation for robot manipulation, outperforming prior methods across benchmarks.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§