paper-with-me

홈 › Papers

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

2024-02-22 · Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang

We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language models, training data and training recipes. Our extensive experiments showed that better quality of data combined with better training recipes, smaller LMMs can consistently achieve on-par performances compared to bigger LMMs. Under our framework, we train a family of small-scale LMMs. Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. We hope our findings can serve as baselines for future research in terms of data scaling, training setups and model selections. Our model weights and codes will be made public.

📄 PDF Abstract BibTeX arXiv:2402.14289

Code (2)

dlcv-buaa/tinyllavabench 공식 구현 pytorch
tinyllava/tinyllava_factory pytorch

Tasks

Visual Question Answering

Similar Papers 제목 키워드 기반

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

2024-05-20 · Junlong Jia, Ying Hu, Xi Weng, Yiming Shi 외

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of train…

Philosophy

TinyLLaVA-Video: A Simple Framework of Small-scale Large Multimodal Models for Video Understanding

2025-01-26 · Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan 외

We present the TinyLLaVA-Video, a video understanding model with parameters not exceeding 4B that processes video sequences in a simple manner, without the need for complex architectures, supporting both fps sampling and…

Video Understanding

TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

2025-04-13 · Xingjian Zhang, Siwei Wen, Wenjun Wu, Lei Huang

Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as ma…

Question Answeringreinforcement-learningReinforcement LearningVideo Understanding

Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning

2025-11-28 · Jiajun Guo, Xin Luo, Jiayin Zheng, Yiqun Wang 외 arxiv

Multimodal foundation models are increasingly trained on sensitive data across domains such as finance, biomedicine, and personal identifiers. However, this distributed setup raises serious privacy concerns due to the ne…

Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models

2026-04-16 · Haoyi Sun, Xiaoxiao Wang, Ning Mao, Qian Wang 외 arxiv

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Dist…

Knowledge Distillation