Scholar
Yumeng Shi
Google Scholar ID: z-jFDGMAAAAJ
Nanyang Technology University
efficient machine learning
multimodality
video understanding
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
33
H-index
3
i10-index
1
Publications
6
Co-authors
0
Publications
7 items
The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
2026
Cited
0
Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
2026
Cited
0
CreditXAI: A Multi-Agent System for Explainable Corporate Credit Rating
2025
Cited
0
Causality Matters: How Temporal Information Emerges in Video Language Models
2025
Cited
0
LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
2025
Cited
0
CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration
2025
Cited
0
Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering
2025
Cited
0
