Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Yao Chen; Yilong Chen; Yinqi Yang; Junyuan Shang; Zhenyu Zhang; Zefeng Zhang; Shuaiyi Nie; Shuohuan Wang; Yu Sun; Hua Wu; Haifeng Wang; Tingwen Liu

doi:10.18653/v1/2026.findings-acl.307

ACL Findings2026

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu

去出版方阅读问 Lune

摘要

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu. Findings of the Association for Computational Linguistics: ACL 2026. 2026.

问 Lune

尽管问，回答会引用原文。

Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。

核心论断
谁在沿用
横向对比
局限

你的问题

Lune 的依据

全文 · 引用它的 1 篇顶会 Paper · 相关的 Paper

获取答案

免费开始，无需绑卡

引用它的顶会 Paper1

Logical Phase Transitions: Understanding Collapse in LLM Logical ReasoningXinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu 等ACL 2026 · 28 次引用

问问它们各自怎么用它

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

摘要

问 Lune

尽管问，回答会引用原文。

引用它的顶会 Paper1

它引用的 Paper35

相关 Paper