Zhenyu Wu

Intern-S2-Preview: Scientific Agentic Foundation Model

Lei Bai, Jiaqi Cao, Chiyu Chen, et al.

MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

Beiyu Xu, Zhenyu Wu, Jiaoyan Chen, et al.

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Zichen Ding, Jiaye Ge, Shufan Jiang, et al.

WorldSample: Closed-loop Real-robot RL with World Modelling

Yuquan Xue, Le Xu, Zeyi Liu, et al.

Single and Multi Truth Data Fusion using Large Language Models

Hira Beril Kucuk, Norman W Paton, Jiaoyan Chen, et al.

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

Haoyuan Deng, Yitong Gao, Yudong Lin, et al.

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency

Shuyang Jiang, Nan Yu, Yiming Zhang, et al.

OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards

Zehao Li, Zhenyu Wu, Yibo Zhao, et al.

OS-Themis is a new framework that helps train AI agents to better interact with graphical user interfaces (like phone apps) by providing more reliable feedback on whether the agent is performing tasks correctly. Instead of using a single judge, it breaks down agent actions into verifiable milestones and cross-checks the evidence before making a decision, similar to how a court system works. When tested on smartphone tasks, this approach improved performance by about 10% during training and 7% when filtering practice data.