Scholar
Yayuan Li
Google Scholar ID: j9mIL4AAAAAJ
University of Michigan
AR-AI Instructional Agent
Instructional Videos
Video Generation
Vision and Language
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
12
H-index
2
i10-index
0
Publications
6
Co-authors
4
list available
Contact
No contact links provided.
Publications
13 items
SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery
2026
Cited
0
NTILC: Neural Tool Invocation via Learned Compression
2026
Cited
0
EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound
2026
Cited
0
Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks
2026
Cited
0
BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
2026
Cited
0
When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
2026
Cited
0
MAGIC: Achieving Superior Model Merging via Magnitude Calibration
2025
Cited
0
Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos
2025
Cited
0
Load more
Resume (English only)
Co-authors
4 total
Jason Corso
Professor of Robotics, Electrical Engineering and Computer Science, University of Michigan
Filippos Bellos
University of Michigan
Wuao Liu
University of Massachusetts, Amherst
Shane Storks
Research Fellow, University of Michigan
