Saved in:
Bibliographic Details
Main Author: Li, Zixi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02631
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915425847083008
author Li, Zixi
author_facet Li, Zixi
contents We introduce Pointer, a novel architecture that achieves linear $O(NK)$ complexity for long-range sequence modeling while maintaining superior performance without requiring pre-training. Unlike standard attention mechanisms that compute $O(N^2)$ pairwise interactions, our approach uses layer-wise pointer chaining where each layer's pointer selection depends on previous layer's pointer positions, creating explicit long-distance connections through pointer chains. We demonstrate that this architecture achieves $2$--$10\times$ speedup on long sequences compared to standard transformers, maintains $>95\%$ accuracy on copy tasks at distances up to 2048 tokens, and learns interpretable pointer patterns that reveal structured dependency modeling. Our experiments on efficiency benchmarks, long-range dependency tasks, and interpretability analysis show that Pointer offers a compelling alternative to attention mechanisms for scenarios requiring efficient long-range modeling without pre-training dependencies.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02631
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pointer: Linear-Complexity Long-Range Modeling without Pre-training
Li, Zixi
Computation and Language
We introduce Pointer, a novel architecture that achieves linear $O(NK)$ complexity for long-range sequence modeling while maintaining superior performance without requiring pre-training. Unlike standard attention mechanisms that compute $O(N^2)$ pairwise interactions, our approach uses layer-wise pointer chaining where each layer's pointer selection depends on previous layer's pointer positions, creating explicit long-distance connections through pointer chains. We demonstrate that this architecture achieves $2$--$10\times$ speedup on long sequences compared to standard transformers, maintains $>95\%$ accuracy on copy tasks at distances up to 2048 tokens, and learns interpretable pointer patterns that reveal structured dependency modeling. Our experiments on efficiency benchmarks, long-range dependency tasks, and interpretability analysis show that Pointer offers a compelling alternative to attention mechanisms for scenarios requiring efficient long-range modeling without pre-training dependencies.
title Pointer: Linear-Complexity Long-Range Modeling without Pre-training
topic Computation and Language
url https://arxiv.org/abs/2508.02631