LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
원문 초록
Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the maximum token limit in large language models (LLMs), leading to increased computational demands and decreased performance when prompts include multiple images or videos. Industry solutions often mitigate this issue by increasing computational power, but this approach is less feasible in academic environments with limited resources. In this study, we propose Dynamic Feature Map Reduction (DFMR) based on LLaVA-1.5 to address the challenge of visual token overload. DFMR dynamically compresses the visual tokens, freeing up token capacity. Our experimental results demonstrate that integrating DFMR into LLaVA-1.5 significantly improves the performance of LLaVA in varied visual token lengths, offering a promising solution for extending LLaVA to handle multi-image and video scenarios in resource-constrained academic environments and it can also be applied in industry settings for data augmentation to help mitigate the scarcity of open-domain image-text pair datasets in the continued pretraining stage.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.