Yin Da Sun

Papers

Total Citations

H-Index

About

Yin Da Sun is a leading researcher in multimodal machine learning and remote inference systems, with a focus on real-time decision-making under dynamic data conditions. Their most-cited work, "Multimodal Remote Inference" (2025), addresses the critical challenge of feature freshness in distributed sensor networks, where multiple data modalities must be processed simultaneously for accurate predictions. By modeling the trade-offs between communication latency, sensor sampling rates, and inference accuracy, Sun has pioneered frameworks that enable efficient, low-latency AI at the edge. This work has already garnered 3 citations in its early release, signaling strong interest from the networked systems and ML communities. Sun’s contributions are particularly impactful for applications in autonomous systems, smart infrastructure, and IoT, where stale data can compromise safety and performance. Their research bridges the gap between theoretical information freshness (age of information) and practical multimodal fusion, offering both analytical insights and deployable algorithms. As a rising voice in this interdisciplinary space, Sun continues to shape how next-generation remote inference systems balance timeliness, reliability, and computational efficiency.