Bowen Yang

OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents

Bowen Yang, Kaiming Jin, Zichen Ding, et al.

Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)

Zilin Du, Bowen Yang, Boyang Albert Li

FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models

Bowen Yang, Jingbo Zhou, Qinghong Miao, et al.

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Kai Chen, Jifeng Ding, Ning Ding, et al.

Intern-S2-Preview: Scientific Agentic Foundation Model

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

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Qiushi Sun, Kanzhi Cheng, Yian Wang, et al.

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

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

Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots

Junda Ying, Yuxuan Wang, Bowen Yang, et al.

Voxtral TTS

Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, 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.