Research Assistant
I contribute to IR research infrastructure through Anserini, Pyserini, and RankLLM, and led QuackIR and rosaOS.
~ se @ uwaterloo · ir & nlp ~
Hello! I'm Lily Ge; I also publish and collaborate under my given name, Yijun Ge. I'm a Software Engineering student at the University of Waterloo. My interests lie in Natural Language Processing (NLP), Information Retrieval (IR), Agentic Systems, and Robots. I am fortunate to be advised by Professor Jimmy Lin.
I contribute to IR research infrastructure through Anserini, Pyserini, and RankLLM, and led QuackIR and rosaOS.
I built RAG pipelines, enabled citation extraction across various model providers, and prepared data for annotation.
Yijun Ge*, Kushaldeep Mujral*, Karthik Nambiar, and Jimmy Lin. 2026. rosaOS: Agentic Operating System for Embodied LLMs. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, July 2026, San Diego, California.
Yijun Ge, Zibo Guo, Sahel Sharifymoghaddam, and Jimmy Lin. 2026. MCP Servers for Pyserini and RankLLM: Enabling Agentic Retrieval-Augmented Generation. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026), July 2026, Melbourne, Australia.
Sahel Sharifymoghaddam*, Yijun Ge*, Raghav Vasudeva, and Jimmy Lin. 2026. Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026), July 2026, Melbourne, Australia.
Yijun Ge, Zijian Chen, and Jimmy Lin. 2025. QuackIR: Retrieval in DuckDB and Other Relational Database Management Systems. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 492-500, November 2025, Suzhou (China).
An AI-driven visual novel with LLM dialogue, RAG-backed long-term memory, local stable diffusion, and custom game logic through a Flask backend.
Webcam-based keyboard input from ASL hand gestures and MediaPipe gesture shortcuts for control keys, with modular AI components and real-time OpenCV video.