ACT-2 Achieves 99.1% Success in Unseen Homes via One-Shot Fine-Tuning
Olivier__OG · x · 2026-08-02
Sunday Robotics introduced its ACT-2 Preview and Memo robot, demonstrating the ability to learn new behaviors from a single fine-tuning example. The robot successfully applied these behaviors in unfamiliar home environments, with the company reporting a 99.1% success rate.
The core challenge in home robotics is generalization: models often fail when room layouts, objects, or lighting change. If robust, this demo signifies a major breakthrough in rapid learning and cross-scenario generalization, paving the way for home robots that can continuously adapt to new tasks.
More from Embodied
- FCC Warns Foreign-Produced Advanced Robots Pose National Security Risks — TechNadu · 2026-08-02
- The Core Problem in Robotics: Maintaining a Coherent Dynamic World Representation — ___Mufasaa · 2026-08-02
- Google DeepMind Launches Gemini Robotics 2 for Whole-Body Robot Intelligence — emmanuelvivier · 2026-08-02
- Awesome AI Hardware: A Curated List of Open-Source AI x Hardware Projects — sujingshen · 2026-08-02
- Humanoids Enter Workplaces Before Dedicated Safety Standards Exist — VraserX · 2026-08-01
- Figure's F.03 Robot Can Now Climb Ladders Fully Autonomously — adcock_brett · 2026-08-01