Scholar
Xiangyu Zhang
Google Scholar ID: yuB-cfoAAAAJ
Co-founder & Chief Scientist of StepFun
Neural Network Architectures
Efficient Deep Learning
Computer Vision
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
343,174
H-index
73
i10-index
104
Publications
20
Co-authors
18
list available
Contact
No contact links provided.
Publications
14 items
MentalThink: Shaping Thoughts in Mental SVG World
2026
Cited
0
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
2026
Cited
0
Skill-Guided Continuation Distillation for GUI Agents
2026
Cited
0
MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
2026
Cited
0
AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications
2026
Cited
0
Vision Foundation Models as Generalist Tokenizers for Image Generation
2026
Cited
0
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
2026
Cited
0
WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics
2026
Cited
0
Load more
Resume (English only)
Co-authors
18 total
Jian Sun
Chief Scientist of Megvii, Managing Director of Megvii Research
Kaiming He
Associate Professor, EECS, MIT
Co-author 3
Tiancai Wang
Dexmal
Tong Yang
Fudan University, Megvii Inc
Zeming Li
Hong Kong University of Science and Technology (HKUST)
Ningning Ma
Unknown affiliation
Gang YU
StepFun