CV
Weijia (Charlie) Zhang
Incoming M.S. in Computer Science @ Yale
Summary
Incoming Yale M.S. student in Computer Science, UIUC Computer Science and Mathematics graduate, and NLP/LLM agent researcher.
Education
- M.S. in Computer Science2028-05Yale University
- B.S. in Computer Science and Mathematics2026-05University of Illinois Urbana-ChampaignGPA: 3.7/4.0
Work Experience
- Research InternJul 2025 - Sep 2025Microsoft Research Asia, MicrosoftWorked on VLM/LLM agent research to improve Microsoft Excel Copilot capabilities.
- Built the TextAnalysisSFT data pipeline for SFT data generation for the new TextAnalysis API in Excel Copilot.
- Mined 2000+ real Kaggle samples, filtered heavy-text sheets, generated queries and Office.js code, and validated outputs with SheetEngine.
- Delivered a dataset that improved Office Script code-generation accuracy by 75%.
- AI EngineerMay 2023 - Jul 2023Reborn NetworkBuilt real-time role-playing agent systems in Unity VR.
- Developed a role-playing agent Unity VR game enabling agents to interact through text, voice, and VR actions in real time with under 1s latency.
- Introduced RAG and vector databases to strengthen long-term agent memory, improving dialogue coherence score from 2/5 to 4/5.
- Designed a reusable character-card framework, enabling a UGC ecosystem and reducing character persona configuration time by 300%.
- Software EngineerAug 2024 - Sep 2024Tencent, WeChat GroupBuilt performance analysis tooling for WeChat Mini Programs and Unity memory profiling.
- Developed a cross-platform Android and iOS hardware performance analysis tool for WeChat Mini Programs, supporting 200+ partner teams in identifying performance bottlenecks.
- Built a Unity Mono Memory Profiler that discovered 40+ hidden memory allocation points, reducing memory-leak-related crash rate by 120%.
Skills
Programming Languages
- Python
- C/C++
- C#
- Java
- JavaScript/TypeScript
- HTML/CSS
- SQL
- Rust
Frameworks and Libraries
- VERL
- VLLM
- LangGraph
- LangChain
- PyTorch
- TensorFlow
AI Focus
- SFT
- Reinforcement Learning
- Post-training
- RAG
- Agentic AI
- Machine Learning
- Generative AI
Publications
- How Much Vision Does Multimodal Reasoning Need? Vision-Stripping for Multimodal Benchmarks2026Under review at NeurIPS 2026Research on vision-stripping for multimodal reasoning benchmarks.
- Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs2026Under review at EMNLP 2026Research on compressed moral composition in frontier LLMs.
- SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning in Text-only LLMs2025arXiv preprint arXiv:2510.25092; under review at EMNLP 2026Agentic information flow for multimodal reasoning in text-only LLMs.
- CUADebug: Diagnosing and Repairing Computer-Use Agent Failures2026Under review at EMNLP 2026A framework for diagnosing and repairing computer-use agent failures.
- Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory2024The First Workshop on AI Behavioral Science, ACM SIGKDD 2024A simulated LLM agent society for studying emergent social contracts.
- Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks2026
- Where LLM Agents Fail and How They Can Learn From Failures2025arXiv preprint arXiv:2509.25370Research on LLM agent failures and learning from failed trajectories.
Portfolio
- OpenManus & OpenManus-RL2025ResearchOpen-source agent research ecosystem with 60,000+ GitHub stars; contributed to OpenManus-RL as a core contributor.
- GUIAgentDebugger2026ResearchSelf-evolving VLM-agent debugging framework with a GUI-agent error taxonomy and dual-layer memory.
Interests
- ResearchLLM agents, VLM/LLM agents, Multimodal reasoning, Agent debugging, Reinforcement learning