XINJI MAI / BACKGROUND个人经历
Curriculum vitae简历
Experience & internships工作与实习经历
2026.07 – Present至今
Tongyi Lab, Alibaba Group阿里巴巴集团 · 通义实验室
Algorithm Engineer · Shanghai算法工程师 · 上海
Agentic reinforcement learning, self-evolving agents, and reasoning.智能体强化学习、自进化智能体与推理能力研究。
2025.05 – 2026.07
Tongyi Lab, Alibaba Group阿里巴巴集团 · 通义实验室
Reinforcement Learning Algorithm Intern · Shanghai强化学习算法实习生 · 上海
Self-evolving agent training, synthetic interaction data, and reward modeling; contributed to AgentEvolver.自进化智能体训练、交互数据合成与奖励建模，参与 AgentEvolver 开源项目。
2024.12 – 2025.05
Xiaohongshu · AGI Group小红书 · AGI 组
Large Language Model Algorithm Intern · Shanghai大模型算法实习生 · 上海
Mathematical reasoning data synthesis and reinforcement learning with code execution, including Agentic RL Scaling Law.数学推理数据合成与代码执行强化学习，参与 Agentic RL Scaling Law 研究。
2024.07 – 2024.12
ByteDance · TikTok字节跳动 · TikTok
Multimodal LLM Algorithm Intern · Shanghai多模态大模型算法实习生 · 上海
Multimodal models and object detection for intellectual-property audits and e-commerce platform governance.面向电商平台治理的知识产权审核、多模态模型训练与目标检测。
Education教育经历
Fudan University复旦大学
Master’s · Computer Technology硕士 · 计算机技术
2023.09 – 2026.06
Sun Yat-sen University中山大学
Bachelor’s · Microelectronics Science and Engineering本科 · 微电子科学与工程
2019.09 – 2023.06
Research & publications研究成果
- Cowork-Gym: Synthesizing Interactive Work Environments at Scale
- Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization
- Customizing Video Portraits via Identity-ActionDecoupling
- Hi-EF: Benchmarking Emotion Forecasting in Human-interaction
- CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL
- AgentEvolver: Towards Efficient Self-Evolving Agent System
- When Small Models Team Up: A Weak-Expert Ensemble Surpassing LLMs for Automated Intellectual-Property Audits
- Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
- D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition
- OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem
- Observe finer to select better: Learning key frame extraction via semantic coherence for dynamic facial expression recognition in the wild
- All Rivers Run into the Sea: Unified Modality Brain-Inspired Emotional Central Mechanism
- From Efficient Multimodal Models to World Models: A Survey
- Empower smart cities with sampling-wise dynamic facial expression recognition via frame-sequence contrastive learning
- Coarse-To-Fine Key Frame Selection for Dynamic Facial Expression Recognition