ZJU-OmniAI

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions1
First seenOct 14, 2026
Last mentioned19d ago

Timeline

1 articles · newest first

VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models

VLA-Δ trains robot policies on physical state transitions and beats π0.5 in real-robot tests.

Hugging Face daily papersOct 14, 20:00 UTC · 19d agoAI research1 · 1 read

Appears with

VLA-Deltaai model · 1
RoboTwinproduct · 1
LIBEROproduct · 1
pi0.5ai model · 1

Entities are extracted by the model from each article. First seen Oct 14, 2026, last mentioned 19d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.