Ant Group's Embodied Video-Action Model Tops Benchmarks
omarsar0 · x · 2026-07-11
Ant Group's embodied AI company @robbyantbrain released a video-action foundation model designed for robot control.
The results provided in the post include:
- An average score of 93.6 on RoboTwin 2.0, surpassing π0.5 and previous VA models
- Only a 0.6 point difference between clean and randomized scenarios
- Requires only 10–15 demonstrations to adapt, and supports cross embodiment transfer
Links to the project page and paper are included, representing a clear research/engineering advancement.
Related event: LingBot-VA/VLA 2.0 Released: Native Embodied Foundation Model(24 posts)→
More from Companies & People
- Google DeepMind Frontier Computation team recruits PhD student researchers in London — PetarV_93 · 2026-10-27
- Aeon's former EVP: AI agents are the most impactful innovation of my lifetime — akumar · 2026-10-27
- Tesla FSD approved in Latvia, the 10th European country; Musk praises smaller nations for moving fastest — elonmusk · 2026-10-27
- AI creator Eduardo joins Reflection AI to work on open-weights intelligence — bigblueboo · 2026-10-27
- Microsoft offers voluntary buyouts to 60,000 employees amid soaring AI infrastructure spending — Polymarket · 2026-10-27
- Musk hails Grok Bot as 'incredibly competent chief of staff' as user automates inbox triage — elonmusk · 2026-10-27