Author

Shuai Li

Observed name: Li, Shuai

Institutions: Tianjin University of Technology, University of Florida, Alibaba Group (China), Beihang University

Observed institutions: Tianjin University of Technology, University of Florida, Alibaba Group (China), Beihang University

OpenAlex ID: A5137686938

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

2026 · Guo, Jiawei, Yu, Donglei, et al. · arXiv (Cornell University) · 5

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

2026 · Jiawei Guo, Yu Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 5

CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding

2026 · Jia, Wei, Lu, Zhicong, et al. · arXiv (Cornell University) · 1

Credit the Right Box: Marginal Contribution Assignment for Structured Visual Perception

2026 · Han, Xinheng, Wang, Jianfei, et al. · arXiv (Cornell University) · 1

HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads

2026 · Liu, Songyang, Yao, Shunyu, et al. · arXiv (Cornell University) · 1

Boosting Multimodal Federated Learning via Chained Modality Optimization

2026 · Zhang, Zixin, Qi, Fan, et al. · arXiv (Cornell University)

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

2026 · Su, Zixian, Zhang, Hongkai, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 13

H-index: 2

I10-index: