Max Robotics — Global Service Robot Directory + US Certification

About

Jiading Fang is a computer vision and robotics researcher whose work spans camera calibration, 3D scene understanding, and the integration of large language models into embodied AI systems. His most-cited contribution, "Self-Supervised Camera Self-Calibration from Video" (2022, 27 citations), addresses a longstanding bottleneck in robotics pipelines by enabling cameras to calibrate themselves automatically from video streams, eliminating the need for laborious manual procedures. This work reflects his broader commitment to making robotic perception more practical and scalable in real-world deployments. Fang has also made notable strides in applying large language models to robotic reasoning. His "Statler" framework (2023–2024, accumulating over 30 citations combined) introduces state-maintaining language models that allow robots to track and update world-state representations during complex tasks—a meaningful advance beyond systems that rely solely on action-observation histories. Complementing this, his "Transcrib3D" work tackles natural language grounding in 3D environments, a critical capability for human-robot collaboration. His research on "DeLiRa" further demonstrates his versatility, pushing the boundaries of self-supervised depth estimation and neural radiance fields under constrained viewpoints. Together, Fang's contributions position him as an emerging voice at the intersection of geometric perception and language-driven robotic intelligence.