FoveaVLA replaces wrist cameras with learned foveation, hitting 70.8% success
Haoyu_Xiong_ · x · 2026-10-16
Researchers introduce FoveaVLA, a VLA that replaces the wrist camera with learned foveation actions: the policy predicts where it needs to look next, then crops that region from a full-resolution external image — the full view gives context, the foveal crop gives close-up detail.
With one external camera and no wrist camera, FoveaVLA reaches 70.8% success on 48 real-world trials, vs. 52.1% for π0.5 with a wrist camera. No additional demonstrations, no camera calibration. Paper, code, and model weights are all open-sourced.
More from Embodied
- Tesla Unveils 'Flying Roadster' Reportedly Equipped with Cold Gas Thrusters — nptacek · 2026-10-16
- AutoAgent0: VLM-powered agentic runtime lifts long-tail driving success by 28.3pp — yining_hong · 2026-10-16
- CarryOn: dual-loop harness adds personalization and safe recovery to frozen VLA robots — Zixuan Wang · 2026-10-16
- Musk teases two-way Grok x Optimus integration: Grok in the bot, bot in Grok — beffjezos · 2026-10-16
- SimVTA uses simulator-rendered video to post-train driving world action models with RL — OpenDriveLab · 2026-10-16
- Robotics data startups compared: Scale AI tops $1B revenue as 9 LLM vs robotics data suppliers benchmarked — FinanceYF5 · 2026-10-16