2 papers
cs.CL2025
Pipelined Decoder for Efficient Context-Aware Text Generation
Zixian Huang, Chenxu Niu, Yu Gu +3
As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also r…
cs.CL2024
MindMerger: Efficient Boosting LLM Reasoning in non-English Languages
Zixian Huang, Wenhao Zhu, Gong Cheng +2
Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-t…