研究人员正在开发新的方法来优化AI模型中视觉分词的使用，特别是对于视觉Transformer和视觉-语言模型。这些方法旨在通过选择性地修剪或压缩不太关键的分词来降低计算成本并提高推理效率。技术包括面向分词的语义通信、基于注意力分数的头部感知修剪以及用于紧凑视频表示的自适应分词选择。目标是在准确性和效率之间取得更好的权衡，使这些模型能够在资源受限的环境中更有效地运行。 AI
影响 这些方法旨在提高大型视觉和视觉-语言模型的效率并降低其计算开销，从而有可能在边缘设备上实现更广泛的部署。
排序理由 多篇arXiv论文介绍了用于优化AI模型中视觉分词处理的新颖方法。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.25410v1 Announce Type: cross Abstract: Token communications realize the semantic communication principle at the granularity of transformer tokens, providing a promising direction for client--server collaborative inference in resource-constrained edge systems. However, …
arXiv:2608.26806v1 Announce Type: new Abstract: With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitigate the computational and context length constraints faced by Large Vision Languag…
arXiv:2608.25332v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have exhibited impressive performance across diverse visual scenarios. However, this success comes at the cost of explosive growth in visual tokens, which imposes substantial memory and computational ov…
arXiv:2603.22991v2 Announce Type: replace Abstract: Efficient visual representation is a central image-processing challenge in embodied manipulation, where policies repeatedly process dense visual-token sequences during closed-loop control. Existing methods rank or prune tokens u…
arXiv:2608.23921v1 Announce Type: new Abstract: Recent Vision-Language Models encode high-resolution images into long visual token sequences, incurring prohibitive prefill costs. To compress them, existing methods score each visual token by averaging text-to-visual attention unif…
arXiv:2608.24293v1 Announce Type: new Abstract: Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with variational autoencoders (VAEs) to enhance computational efficiency without compromisi…
arXiv:2608.23864v1 Announce Type: new Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be organized to facilitate denoising remains underexplored. In this paper, we define t…