cs.AI updates on arXiv.org 09月12日
TreeGPT:无注意力机制的结构化推理新架构
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出TreeGPT,一种无注意力机制的网络架构,旨在结构化推理任务中探索纯TreeFFN编码器-解码器设计的潜力。TreeGPT在ARC Prize 2025数据集上取得了99%的验证准确率,表明在特定任务中,TreeFFN架构可能优于基于注意力的方法。

arXiv:2509.05550v2 Announce Type: replace Abstract: We present TreeGPT, an attention-free neural architecture that explores the potential of pure TreeFFN encoder-decoder design for structured reasoning tasks. Unlike traditional transformer approaches that rely on attention mechanisms, TreeGPT employs bidirectional TreeFFN components that process sequences through adjacent connections in parallel, aiming to achieve computational efficiency while maintaining reasoning capabilities. Our approach centers on a TreeFFN Encoder-Decoder mechanism: $$\text{Encoder TreeFFN (L} \rightarrow \text{R)} + \text{Decoder TreeFFN (R} \leftarrow \text{L)} \rightarrow \text{Parallel Processing}$$ where the encoder processes left-to-right dependencies while the decoder handles right-to-left patterns, both using simple neighbor-to-neighbor connections. This design eliminates attention computation while maintaining sequence modeling capabilities. We evaluate our approach on the ARC Prize 2025 dataset, where TreeGPT achieves 99\% validation accuracy using 3.16M parameters. The model converges within 1500 training steps and demonstrates 100\% token-level accuracy on selected evaluation samples. Our preliminary results suggest that for certain structured reasoning tasks, specialized TreeFFN architectures may offer advantages over attention-based approaches. While these findings are encouraging, we acknowledge that further investigation across diverse tasks and datasets would be valuable to establish the broader applicability of attention-free designs.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

TreeGPT 结构化推理 TreeFFN 无注意力机制 神经网络
相关文章