logo
today local_bar
Hybrid Neural Architectures;Long Sequence Models;State Space Models;Linear Recurrent Neural Networks

1 paper across 1 session

Poster Session 1

1 paper
Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
#3510 · Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, yelong shen

A hybrid architecture with linear pre-filling complexity and up-to10x higher throughput on decoding.