Scholar

Junyang Wang

Google Scholar ID: m4ro0NsAAAAJ

Beijing Jiaotong University

Multi-modal LearningMLLMAgent

Citations & Impact

All-time

Citations

1,988

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

18 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published papers: 'Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation' accepted by NeurIPS 2025; 'Mobile-Agent-v3' achieved SOTA performance on 10 GUI benchmarks; 'PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC' accepted by ICLR 2025 Workshop; 'Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration' accepted by NeurIPS 2024; 'Mobile-Agent' won the best demo award at CCL 2024; 'Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception' accepted by ICLR 2024 Workshop; 'Improved Visual Fine-tuning with Natural Language Supervision' accepted by ICCV 2023 Oral; 'From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping' accepted by IJCAI 2023; 'Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models' accepted by MM 2022.

Research Experience

Research intern at Tongyi AI Lab, Alibaba Group; involved in multiple research projects including the Mobile-Agent series and PC-Agent.

Education

Ph.D. candidate, School of Computer and Information Technology, Beijing Jiaotong University, Advisor: Prof. Jitao Sang.

Background

Research Interests: Multi-modal Large Language Models (MLLMs), MLLMs hallucination, MLLM-based agents, Vision-Language Pre-training (VLP), social fairness in computer vision.

Miscellany