Wenjie Shi

3 papers · 2019–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze

Venues

ACL (1) IJCAI (1) NeurIPS (1)

Top co-authors

Cheng Wu (2) Shiji Song (2) Liang Pang (1) Jingcheng Deng (1) Jingang Wang (1) Hui Wu (1) Shicheng Xu (1) Gao Huang (1) Zenghao Duan (1) Jiahao Liu (1)

Research topics

Reinforcement Learning (2) Methods (2) Artificial Intelligence (1) Deep Learning (1) Machine Learning (1) Core AI (1) Learning Types (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

deep reinforcement learning (2) sample efficiency (1) maximum entropy (1) policy gradient (1) function approximation (1) policy iteration (1) off-policy learning (1) continuous action space (1) anderson acceleration (1) soft value function (1) test-time scaling (1) reasoning dynamics (1) off-policy deep rl (1) overthinking detection (1) early-exit method (1) reasoning completion point (1)

Papers

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis ACL 2026 Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning NeurIPS 2019 Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning IJCAI 2019