Papers

1

Total Citations

18

H-Index

1

About

Seokchan Song is a rising star in the field of energy-efficient artificial intelligence hardware, with a primary focus on enabling real-time spatial computing for mobile and embedded systems. His most prominent contribution is the development of "Space-Mate," a groundbreaking 303.5mW real-time processor that integrates a sparse Mixture-of-Experts (MoE) architecture with Neural Radiance Fields (NeRF) for Simultaneous Localization and Mapping (SLAM). This work, published in 2024 and already garnering 18 citations, directly addresses the critical challenge of deploying complex 3D scene understanding on power-constrained devices like autonomous robots and augmented reality (AR) glasses. By achieving a remarkable balance between computational efficiency and high-fidelity 3D reconstruction, Song’s processor enables accurate user positioning and environmental mapping without the prohibitive energy costs of traditional systems. His research sits at the intersection of computer architecture, machine learning, and spatial computing, promising to unlock new capabilities for mobile spatial intelligence. As a researcher pushing the boundaries of on-device AI, Song’s work is pivotal for the next generation of immersive and autonomous technologies.

Research Focus

Key Achievements

1
H-Index
1
Papers
18
Total Citations
18
Avg Citations/Paper
🏆 Most Cited Paper
20.8 Space-Mate: A 303.5mW Real-Time Sparse Mixture-of-Experts-Based NeRF-SLAM Processor for Mobile Spatial Computing
18 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: Korea Advanced Institute of Science and Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago