Wenjie Qiu
About Me
Hi, I'm Wenjie Qiu (邱文杰). I recently completed my Ph.D. in Computer Science at Rutgers University and now work as an Applied Scientist at Amazon. Before that, I earned an M.S. in Computer Science from Washington University in St. Louis and a B.E. in Electronic Information Engineering from Central China Normal University. My industry experience includes internships at Amazon, LinkedIn, and Samsung Research America. My research spans Reinforcement Learning, AI Agent, Preference Learning, and Large Language Models.
I’m always open to new research ideas and collaborations. If my work aligns with your interests, I’d love to connect.
News
- [2026.02] Join Amazon as an Applied Scientist at New York City.
- [2026.01] One paper is accepted to ICLR'26.
- [2026.01] Invited as a reviewer for ICLR 2026 Workshop ES-Reasoning.
- [2026.01] Graduated from Ph.D. in Computer Science at Rutgers University.
- [2026.01] Invited as a reviewer for ICML 2026.
- [2025.11] Successfully defended Ph.D. dissertation.
- [2025.09] Two papers are accepted to NeurIPS'25.
- [2025.09] Join Amazon as an Applied Scientist Intern.
- [2025.09] Invited as a reviewer for ICLR 2026.
- [2025.08] Invited as a reviewer for AISTATS 2026.
- [2025.05] Join LinkedIn as a PhD AI/ML Intern.
- [2025.02] Invited as a reviewer for NeuS 2025.
- [2025.02] Invited as a reviewer for NeurIPS 2025.
- [2025.01] Invited as a reviewer for ICLR 2025 Workshop VerifyAI.
- [2024.11] Invited as a reviewer for AISTATS 2025.
- [2024.09] Invited as a reviewer for TNNLS.
- [2024.08] Invited as a reviewer for TIST.
- [2024.06] Invited as a reviewer for NeurIPS 2024.
- [2024.04] One paper is accepted at PLDI'24.
- [2023.12] Present our work on program synthesis on RL agent at NeurIPS'23 in New Orleans.
- [2023.09] One paper is accepted to NeurIPS'23.
Earlier news
- [2023.03] Successfully passed Ph.D. qualifying exam.
- [2022.05] Join Samsung Research America as a Research Intern.
- [2022.05] Present our work on programmatic reinforcement learning at ICLR'22.
- [2022.04] Invited talk on programmtic reinforcement learning at RLChina.
- [2022.01] One paper is accepted to ICLR'22 as a Spotlight presentation.
- [2020.09] Join Rutgers Automated Reasoning Lab as a Research Assistant.
- [2020.09] Start Ph.D. in Computer Science at Rutgers University.
- [2020.05] Complete M.S. in Computer Science at Washington University in St. Louis.
- [2019.06] Start a research internship at S3 Lab at Stevens Institute of Technology.
- [2019.01] Join Computer Security & Privacy Lab as a Research Assistant.
- [2018.08] Start M.S. in Computer Science at Washington University in St. Louis.
Research Interests
- Reinforcement Learning
- Large Language Models
- Program Synthesis
- Embodied AI
- Agentic Systems
Education
- Rutgers University, Ph.D. in Computer Science
- Washington University in St. Louis, M.S. in Computer Science
- Central China Normal University, B.E. in Electronic Information Engineering
Publications (* indicates equal contribution)
-
ICLR'26
International Conference on Learning Representations (ICLR), 2026. -
NeurIPS'25
Neural Information Processing Systems (NeurIPS), 2025. -
NeurIPS'25
Neural Information Processing Systems (NeurIPS), 2025. -
PLDI'24
Programming Language Design and Implementation (PLDI), 2024. -
NeurIPS'23
Neural Information Processing Systems (NeurIPS), 2023. -
ICLR'22
International Conference on Learning Representations (ICLR), 2022. [Spotlight]
Recent Submissions (Under Review)
- FinLCR: Scaling Financial Long-Context Reasoning via Curriculum Reinforcement Learning (ACL)
- Compositional Policy Optimization with Language Models (AAAI)
Honors & Awards
- Spotlight Presentation, ICLR 2022 (Top 3%)
- Boya Scholarship, Central China Normal University (Top 3%)
Academic Service
- Conference Reviewer: NeurIPS 2024–2025, ICLR 2025–2026, ICML 2026, AISTATS 2025–2026, NeuS 2025
- Journal Reviewer: TIST, TNNLS