Shouren Wang

PhD Student

Shouren Wang is a Ph.D. student in Computer Science at Case Western Reserve University, advised by Prof. Xiaotian Han and Prof. Vipin Chaudhary. His research focuses on large language model reasoning, post-training, model architecture, and AI agent systems.

Education

Ph.D. in Computer Science, Case Western Reserve University, 2024–Present
M.S. in Computer Engineering, New York University, 2023
B.E. in Digital Media Technology, Hunan University, 2019

My current work broadly concerns large language model reasoning, post-training, model architecture, and AI agent systems.

Before joining Case Western Reserve University, he earned an M.S. in Computer Engineering from New York University and a B.E. in Digital Media Technology from Hunan University.

Large language model reasoning, post-training, model architecture, and AI agent systems.

Current Projects

How to Loop MoE

Studies when recurrent depth benefits Mixture-of-Experts language models, how expert and attention parameters should be shared across loops, and what router behavior reveals about repeated computation.

Hybrid Thinking and Controllable Reasoning

Studies how language models switch between fast and deliberative modes, from diagnosing reasoning leakage and training-data effects to architecture-level separation of reasoning pathways.

Learn More

Agent Team Work Zone

Develops persistent workspaces, checkpoints, and recovery workflows for long-lived Claude Code agent teams.

Learn More

Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation

2026

Shouren Wang* , Wang Yang* , Chuang Ma , Debargha Ganguly , Vikash Singh , Chaoda Song , Xinpeng Li , Xianxuan Long , Vipin Chaudhary , Xiaotian Han

Conference on Language Modeling (COLM 2026)

Large Language Models Model Architecture Reasoning

arXiv Code

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?

2026

Shouren Wang* , Wang Yang* , Xianxuan Long , Qifan Wang , Vipin Chaudhary , Xiaotian Han

EMNLP 2026 Main Conference

Large Language Models Post-Training Reasoning

arXiv Code

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers

2026

Van Yang* , Shouren Wang* , Debargha Ganguly , Xinpeng Li , Chaoda Song , Vikash Singh , Vipin Chaudhary , Xiaotian Han

Findings of the Association for Computational Linguistics: ACL 2026

Large Language Models Reasoning Inference Efficiency

arXiv Code View

A Survey on Efficient Protein Language Models

2026

Shouren Wang , Debargha Ganguly , Vinooth Rao Kulkarni , Wang Yang , Zhuoran Qiao , Daniel Blankenberg , Vipin Chaudhary , Xiaotian Han

Transactions on Machine Learning Research (TMLR 2026)

Protein Language Models Efficient AI Survey

OpenReview Code

Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams

2026

Shouren Wang

arXiv preprint

AI Agents Agent Infrastructure Persistent Workspaces

arXiv Code

Mentors

Xiaotian Han

Kevin J. Kranzusch Assistant Professor, Department of Computer and Data Sciences, Case School of Engineering

Vipin Chaudhary, PhD

Kevin J. Kranzusch Chair, Computer and Data Sciences,
Center for PEATAI, Case School of Engineering