paper-with-me

홈 › Papers

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory

2024-04-17 · Zicheng Liu, Li Wang, Siyuan Li, Zedong Wang, Haitao Lin, Stan Z. Li

Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Although there are existing attention variants that improve computational efficiency, they have a limited ability to abstract global information effectively based on their hand-crafted mixing strategies. On the other hand, state-space models (SSMs) are tailored for long sequences but cannot capture complicated local information. Therefore, the combination of them as a unified token mixer is a trend in recent long-sequence models. However, the linearized attention degrades performance significantly even when equipped with SSMs. To address the issue, we propose a new method called LongVQ. LongVQ uses the vector quantization (VQ) technique to compress the global abstraction as a length-fixed codebook, enabling the linear-time computation of the attention matrix. This technique effectively maintains dynamic global and local patterns, which helps to complement the lack of long-range dependency issues. Our experiments on the Long Range Arena benchmark, autoregressive language modeling, and image and speech classification demonstrate the effectiveness of LongVQ. Our model achieves significant improvements over other sequence models, including variants of Transformers, Convolutions, and recent State Space Models.

📄 PDF Abstract BibTeX arXiv:2404.11163

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyLanguage ModelingLanguage ModellingQuantizationState Space Models

Similar Papers 제목 키워드 기반

LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models

2026-07-01 · Arpita Nema, Hanwei Zhu, Xi Zhang, Weisi Lin arxiv

The evaluation of long-term video quality understanding remains an open challenge for large vision-language models (LVLMs). Existing video quality benchmarks predominantly focus on short clips and isolated distortions, o…

FoldToken: Learning Protein Language via Vector Quantization and Beyond

2024-02-04 · Zhangyang Gao, Cheng Tan, Jue Wang, Yufei Huang 외

Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of di…

Quantization

Vector Quantization in the Brain: Grid-like Codes in World Models

2025-10-16 · Xiangyuan Peng, Xingsi Dong, Si Wu arxiv

We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attractor dynamics. Unlike conventional vector …

Autoregressive Image Generation using Residual Quantization

2022-03-03 · CVPR 2022 1 · Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho 외

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational c…

Conditional Image GenerationImage GenerationImage ReconstructionQuantization+1

Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization

2026-03-17 · Wenhao Zhao, Qiran Zou, Zhouhan Lin, Dianbo Liu arxiv

Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discr…