Weize Kong

I'm a researcher at OpenAI, working on agents 🤖.  Previously, I was a Staff Research Scientist at Google DeepMind, where I focused on knowledge augmentation ( retrieval-augmented generation and long-context models) and personalization for LLMs. Before Google, I was a Ph.D. student advised by Prof. James Allan at Center for Intelligent Information Retrieval (CIIR), University of Massachusetts Amherst. Prior to CIIR, I worked with Prof. Yiqun Liu, in the Information Retrieval Group, Tsinghua University.

Recent Publications (All)

• Alireza Salemi, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Weize Kong, Tao Chen, Zhuowan Li, Michael Bendersky, Hamed Zamani. Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation. arXiv preprint arXiv:2501.04167, 2025 [paper].

• Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky. Bridging the Preference Gap between Retrievers and LLMs. To appear in Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024 (ACL '24) [paper].

• Weize Kong, Spurthi Amba Hombaiah, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky. PRewrite: Prompt Rewriting with Reinforcement Learning. To appear in Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024 (ACL '24) [paper].

• Gemini Team, Google. Gemini: A Family of Highly Capable Multimodal Models. In arXiv, 2023 [paper].

• Weize Kong, Jeffery M. Dudek, Cheng Li, Mingyang Zhang and Michael Bendersky. SparseEmbed: Learning Sparse Lexcial Representations with Contextual Embeddings for Retrieval. In Proceedings of the 46th ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023) [paper]. 🏆 Best short paper.

• Weize Kong, Swaraj Khadanga, Cheng Li, Shaleen Kumar Gupta, Mingyang Zhang, Wensong Xu and Michael Bendersky. Multi-Aspect Dense Retrieval. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022) [paper].

• Chen Qu, Weize Kong, Liu Yang, Mingyang Zhang, Michael Bendersky and Marc Najork. Natural Language Understanding with Privacy-Preserving BERT. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) [paper].