Kairui Shi

New York University

Papers

1

Total Citations

4

H-Index

1

About

Kairui Shi is a pioneering researcher at the intersection of embodied intelligence and multimodal perception, with a focus on enabling robots to reason about and reconstruct their physical environments. His most notable contribution is **FusionSense**, a groundbreaking framework that bridges common sense, vision, and tactile sensing for robust 3D reconstruction from highly sparse visual data. By fusing priors from large foundation models with limited sensory input, this work addresses a fundamental challenge in robotics—how to make sense of the world with incomplete information, much like humans do. Though recently published in 2025, the paper has already garnered 4 citations, signaling strong early impact. Shi’s research sits at the nexus of computer vision, robotics, and cognitive science, pushing the boundaries of how machines can integrate disparate modalities for scene understanding. His work is particularly relevant for applications in autonomous manipulation, where sparse-view reconstruction and tactile feedback are critical. With a clear trajectory toward more human-like machine perception, Shi is emerging as a key voice in the next generation of embodied AI researchers.

Research Focus

Key Achievements

1
H-Index
1
Papers
4
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
Fusionsense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction
4 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 9
🏛 Institutions: New York University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago