Author

Zhengyang Wang

Observed name: Wang, Zhengyang

Institutions: Amazon (United States), Jilin University, Beijing Information Science & Technology University

Observed institutions: Amazon (United States), Jilin University, Beijing Information Science & Technology University

OpenAlex ID: A5138212393

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

2026 · Li, Siting, Wang, Zhengyang, et al. · arXiv (Cornell University)

H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions

2026 · Zhu, Shiping, Yang, Yibo, et al. · arXiv (Cornell University)

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning

2026 · Lin, Haihao, Huang, Xiangsheng, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: