DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng 0002. DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar, editors, Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025. pages 20544-20552, Association for Computational Linguistics, 2025. [doi]

This author has not been identified. Look up 'Shaoshen Chen' in GoogleThis author has not been identified. Look up 'Yangning Li' in GoogleThis author has not been identified. Look up 'Zishan Xu' in GoogleThis author has not been identified. Look up 'Yongqin Zeng' in GoogleThis author has not been identified. Look up 'Shunlong Wu' in GoogleThis author has not been identified. Look up 'Xinshuo Hu' in GoogleThis author has not been identified. Look up 'Zifei Shan' in GoogleThis author has not been identified. Look up 'Xin Su' in GoogleThis author has not been identified. Look up 'Jiwei Tang' in GoogleThis author has not been identified. Look up 'Yinghui Li' in GoogleThis author has not been identified. Look up 'Hai-Tao Zheng 0002' in Google

runs on WebDSL