G³VLA injects calibrated multi-camera geometry into VLA models to improve manipulation
Yue Peng · hf · 2026-10-15
G³VLA injects calibrated multi-camera geometry into vision-language-action models via ray embeddings and cross-view fusion, improving robot manipulation without changing the action space. The paper details a two-stage training recipe: pre-training a camera-aware geometric module via distillation from a geometry teacher with an auxiliary point-map head, then full policy finetuning with combined action and distillation losses.
More from Embodied
- Gracia's new world model targets Real2Sim2Real and Physical AI — jonstephens85 · 2026-10-15
- Niantic Spatial built VPS on Pokémon Go imagery; a dev already prototyped it solo — jonstephens85 · 2026-10-15
- RoboParty launches RP1, a fully open-source full-stack humanoid robotics platform — GuanyaShi · 2026-10-15
- Survey: Towards Agentic Robots organizes the field into 17 categories across four domains — Chonghan Qin · 2026-10-15
- HumanoidToolBench benchmarks humanoid tool use from selection to mobile execution on real Unitree G1 — snupilab · 2026-10-15
- RegisterWAM adds learnable registers to world action models, hitting 81.6% on LIBERO-Plus and 93% on RoboTwin 2.0 — AutoLab-SJTU · 2026-10-15