paper-with-me

Papers

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference

2025-12-15 · Shengling Qin, Hao Yu, Chenxin Wu, Zheng Li, Yizhong Cao, Zhengyang Zhuge, Yuxin Zhou, Wentao Yao, Yi Zhang, Zhengheng Wang, Shuai Bai, Jianwei Zhang, Junyang Lin arxiv

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic approaches, we formally identify the cumulative reuse error effect and demonstrate how to minimize the non-prefix cache reuse error effectively. We further analyze the varying importance of model layers and propose a dynamic, layer-aware recomputation strategy to balance accuracy and efficiency. Experimental results show that VLCache achieves an accuracy on par with full recomputation, while requiring only 2-5% of the tokens to compute, yielding 1.2x-16x TTFT speedups. We develop an experimental implementation of the proposed VLCache pipeline based on SGLang, enabling significantly faster inference in practical deployments.

📄 PDF Abstract BibTeX arXiv:2512.12977

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference

2025-07-22 · Haoyue Zhang, Jie Zhang, Song Guo arxiv

Although vision transformers (ViT) have shown remarkable success in various vision tasks, their computationally expensive self-attention hinder their deployment on resource-constrained devices. Token reduction, which dis…

RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models

2025-09-25 · Jiyeon Koo, Taewan Cho, Hyunjoon Kang, Eunseom Pyo 외 arxiv

Vision-Language-Action (VLA) models have demonstrated robust performance across diverse robotic tasks. However, their high memory and computational demands often limit real-time deployment. While existing model compressi…

Spatial ReasoningModel Compression

Transfer Learning Applied to Computer Vision Problems: Survey on Current Progress, Limitations, and Opportunities

2024-09-12 · Aaryan Panda, Damodar Panigrahi, Shaswata Mitra, Sudip Mittal 외

The field of Computer Vision (CV) has faced challenges. Initially, it relied on handcrafted features and rule-based algorithms, resulting in limited accuracy. The introduction of machine learning (ML) has brought progres…

Transfer Learning

Simple o3: Towards Interleaved Vision-Language Reasoning

2025-08-16 · Ye Wang, Qianglong Chen, Zejun Li, Siyuan Wang 외 arxiv

Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o…

Multimodal ReasoningVisual GroundingVisual ReasoningImage Cropping

Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement

2026-02-03 · Weikang Qiu, Huashuo Lei, Tinglin Huang, Rex Ying arxiv

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observati…