Publications
16 works, newest first
2026
-
OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration
-
OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
-
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
-
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
-
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
-
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
-
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
-
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
-
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents
2025
-
OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models
-
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
-
MMBench-GUI: A Unified Hierarchical Evaluation Framework for Multi-Platform GUI Agents
-
Intelligent deepwater energy development: Flow assurance monitoring and smart decision-making system
2024
Education
- Sep 2025 – present
- University of Science and Technology of ChinaPhD in Information and Communication Engineering · School of Information and Communication EngineeringJoint training with the Vision-Language Multimodal Team, LLM Center, Shanghai AI Laboratory.
- Sep 2021 – Jun 2025
- Beihang UniversityB.E. in Computer Science and Technology · School of Computer Science and Engineering
- Sep 2018 – Jun 2021
- Tianjin Nankai High School
Interests
My research interests include multimodal large language models, computer-using agents, and coding agents.
Outside of research, I play guitar and enjoy MOBAs, action RPGs and card games. Soulslikes are a particular favorite.
Contact
- bz25006014@mail.ustc.edu.cn (preferred)
21373037@buaa.edu.cn
yangbowen@pjlab.org.cn - GitHub
- YangYzzzz
- a1522708771