Jingxiao Chen

Papers

Total Citations

H-Index

About

Jingxiao Chen is an emerging researcher at the intersection of computer vision, depth estimation, and intelligent decision-making systems. Their work spans two ambitious frontiers: advancing visual perception through foundation models and tackling the complexities of real-world autonomous decision-making. Chen's most recognized contribution introduces a novel prompting paradigm for depth foundation models, specifically adapting the powerful Depth Anything framework to achieve accurate metric depth estimation at 4K resolution. By pioneering the application of prompting techniques — well-established in language and vision models — to depth estimation, Chen has opened a compelling new research direction with practical implications for robotics, autonomous driving, and augmented reality. This work has already garnered 15 citations since its 2025 publication, signaling rapid uptake within the community. Complementing this, Chen's 2023 work addresses the formidable challenge of deploying intelligent decision-making systems in unpredictable, dynamic environments, proposing a foundation model perspective that emphasizes continuous skill acquisition and generalization. Together, these contributions reflect a researcher committed to bridging theoretical foundations with real-world applicability, making Chen a promising voice in the next generation of AI systems research.