Scholar
Mingda Zhang
Google Scholar ID: 4aIwj4QAAAAJ
Google DeepMind
Computer Vision
Multi-modal Understanding
Video Generation
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
729
H-index
10
i10-index
10
Publications
20
Co-authors
14
list available
Contact
GitHub
Open ↗
Publications
21 items
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
2026
Cited
0
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
2026
Cited
0
CollabFlow: Recursive Self-Improvement of Agent Collaboration
2026
Cited
0
JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion
2026
Cited
0
R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution
2026
Cited
0
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
2026
Cited
0
CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ Segmentation
2026
Cited
0
FlowSteer: Interactive Agentic Workflow Orchestration via End-to-End Reinforcement Learning
2026
Cited
0
Load more
Co-authors
11 total
Adriana Kovashka
Associate Professor, University of Pittsburgh
Keren Ye
Google
Rebecca Hwa
Computer Science, The George Washington University
Chris Thomas
Virginia Tech
Yukun Zhu
Google
Milos Hauskrecht
Professor of Computer Science, University of Pittsburgh
Meiqi Guo
Google Deepmind
Malihe Alikhani
Northeastern University & Brookings
