Publications

(2025). MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation. Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025).
(2024). QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory. arXiv preprint arXiv:2408.10497.
(2024). QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression. The 30th China Conference on Information Retrieval (CCIR 2024).