Hosu Lee

Orcid: 0009-0008-4494-2944

Affiliations:

Korea Advanced Institute of Science & Technology (KAIST), Daejeon, South Korea

According to our database¹, Hosu Lee authored at least 4 papers between 2024 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding.

[BibT_eX]

[DOI]

CoRR, March, 2026

2025

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding.

[BibT_eX]

[DOI]

CoRR, June, 2025

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Look Every Frame All at Once: Video-Ma<sup>2</sup>mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing.

[BibT_eX]

[DOI]

CoRR, 2024

Hosu Lee

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...