Working Experience and Education: Now I study at the School of Data Science, Chinese University of Hong Kong, Shenzhen (CUHK-SZ), as a computer science fourth-year PhD candidate under the supervision of Prof Guiliang Liu. I have received my Bachelor’s degree from the School of Computer Science and Technology, Beijing University of Posts and Telecommunications (BUPT). I am currently interning at JD Technology.

Research Interests: Reinforcement Learning and the related topics, including:
● Real-World Reinforcement Learning
● Embodied Agent System
● Humanoid Loco-manipulation

My work has been published in top-tier international AI conferences such as ICLR, ICML, and NeurIPS. Please feel free to communicate and cooperate via email or WeChat.

📖 Educations

Chinese University of Hong Kong, Shenzhen, China Ph.D. in Computer Science Aug. 2023 – Present Supervisor: Prof Guiliang Liu

Beijing University of Posts and Telecommunications, China Bachelor in Computer Science and Technology Aug. 2019 – Jun. 2023

🔥 News

● 2026.09: 🎉 One paper about Human-in-the-loop Real-World Reinforcement Learning accepted by NeurIPS 2026.
● 2026.07: 🎉 One paper about Safety-critical scenario generation accepted by IEEE Transactions on Artificial Intelligence.
● 2026.06: 🎉 Get JingDong TGT (Tech Genius Team) Internship offer.
● 2026.06: 🎉 Two papers about Sim2Real locomotion and robotic skill reuse accepted by IROS 2026.
● 2026.05: 🎉 One paper about Human-in-the-loop Real-World Reinforcement Learning accepted by ICML 2026.
● 2026.04: 🎉 One paper about Agent Error Recovery for Robotic Manipulation accepted by RSS 2026.
● 2026.01: 🎉 One paper about Sim-to-Real human-robot interaction accepted by ICRA 2026.
● 2026.01: 🎉 One paper about Sim-to-Real reinforcement learning humanoid locomotion accepted by ICLR 2026.
● 2025.12: 🎉 Top 1.3% (6/463) in the Tencent AI Arena Global Open Competition (Reinforcement Learning Embodied-AI Track).
● 2024.07: 🎉 One paper about multi-vehicle interaction with game theory accepted by ECCV 2024.
● 2023.09: 🎉 One paper about inverse constrained reinforcement learning accepted by NeurIPS 2023.

📝 Selected Publications

$*$ denotes equal contribiton, $\dagger$ denotes corresponding author

NeurIPS 2026

• Guanren Qiao, Ruixiang Ouyang, Sheng Xu, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu $^\dagger$
• Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation (NeurIPS 2026)
• [paper] [code] [demo]

ICML 2026

• Guanren Qiao, Ruixiang Ouyang, Sheng Xu, Ruixing Jin, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu$^\dagger$
• Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement Learning (ICML 2026)
• [paper] [code] [demo]

ICRA 2026

• Guanren Qiao, Sixu Lin, Ronglai Zuo, Zhizheng Wu, Kui Jia, Guiliang Liu$^\dagger$
• SignBot: Learning Human-to-Humanoid Sign Language Interaction (ICRA 2026)
• [paper] [code] [demo]

ICLR 2026

• Sixu Lin, Guanren Qiao, Yunxin Tai, Ang Li, Kui Jia, Guiliang Liu$^\dagger$
• HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion (ICLR 2026)
• [paper] [code] [demo]

IEEE Transactions on Artificial Intelligence

• Guanren Qiao, Guorui Quan, Jiawei Yu, Shujun Jia$^\dagger$, Guiliang Liu$^\dagger$
• TrafficGamer: Reliable and Flexible Traffic Simulation for Safety-Critical Scenarios with Game-Theoretic Oracles (IEEE Transactions on Artificial Intelligence)
• [paper] [code] [demo]

ECCV 2024

• Guanren Qiao, Guorui Quan, Rongxiao Qu, Guiliang Liu$^\dagger$
• Modelling Competitive Behaviors in Autonomous Driving Under Generative World Model (ECCV 2024)
• [paper] [code]

NeurIPS 2023

• Guanren Qiao, Guiliang Liu$^\dagger$, Pascal Poupart, Zhiqiang Xu
• Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations (NeurIPS 2023)
• [paper] [code]

🏅 Honor

• 2026.08 🏅 Duan Yong Ping Meritorious Travel Award (CNY 10000)
• 2026.06: 🏅 JingDong TGT (Tech Genius Team) Internship
• 2025.12: 🏆 Top 1.3% (6/463) in the Tencent AI Arena Global Open Competition (Reinforcement Learning Embodied-AI Track) (CNY 15000)
• 2024.11 🏅 Duan Yong Ping Meritorious Research Award (CNY 5000)
• 2022.12 🏅 The Chinese University of Hong Kong Shenzhen Scholarship (CNY 6000)
• 2021.10 🏆 Gold Prize, China Internet Plus Innovation and Entrepreneurship National Competition (CNY 20000)
• 2020-2022 🏅 Beijing University of Posts and Telecommunications Merit Student (CNY 500)
• 2020-2022 🏅 Beijing University of Posts and Telecommunications Scholarship (CNY 3000)

💻 Intern

JD Technology, China Embodied-AI Algorithm Intern Aug. 2026 – Now

DexForce Technology, China Embodied-AI Research Intern Aug. 2025 – July 2026

Wangxuan Institute of Computer Technology, Peking University, China Research Assistant Mar. 2022 – Nov. 2022 Supervisor: Prof Xiaoqing Lyu

🖋️ Service

• Conference Reviewer:
  • AAAI (2024, 2026), ICLR (2026), ICCV (2025), NeurIPS (2025, 2026), ICRA (2026)
• Journal Reviewer:
  • IEEE Transactions on Artificial Intelligence (T-AI)
  • Robotics and Computer-Integrated Manufacturing (RCIM)
  • IEEE Transactions on Multimedia (T-MM)