metadata

license: mit
datasets:
  - OpenGVLab/V2PE-Data
language:
  - en
base_model:
  - OpenGVLab/InternVL2-2B
new_version: OpenGVLab/V2PE
library_name: transformers
tags:
  - V2PE

V2PE

[⭐️Project Page] [📜 ArXiv Paper] [📂 GitHub] [📖 HF Datasets]

Introduction

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents.

To address this issue, we propose Variable Visual Position Encoding (V2PE), a novel positional encoding approach that employs variable and smaller increments for visual tokens. Our experiments demonstrate the effectiveness of V2PE to enhances VLMs' ability to effectively understand and reason over long multimodal contexts. We further integrate V2PE with our augmented long-context multimodal datasets to finetune the open-source VLM, InternVL2-2B. The finetuned model achieves strong performance on both standard and long-context multimodal tasks. Notably, when the sequence length of the training dataset is increased to 256K tokens, the model is capable of processing multimodal sequences up to 1M tokens, highlighting its potential for real-world long-context applications.

This repository contains the instruction-tuned V2PE-32K-InternVL-2B model and V2PE-256K-InternVL-2B model, which have 1.8B activated parameters (3B in total) and are trained on V2PE-Data. It is built upon InternVL2-2B. For more details, please refer to our paper.

Performance

General MLLM Benchmarks

Model	#Param	ChartQA	DocVQA	AI2D	InfoVQA	SQA	POPE	MMMU_val	MMBench_EN	SEED_I	Avg
InternVL2-2B	2.0B	71.7	86.9	74.1	58.9	94.1	85.2	36.3	73.4	70.9	72.4
DeepSeek-VL-1.3B	2.0B	47.4	-	51.5	-	68.4	85.9	33.8	66.4	66.0	-
Qwen2-VL-2B	2.0B	73.5	90.1	74.7	65.5	-	-	41.1	74.9	-	-
Aquila-VL-2B	2.2B	32.0	85.0	75.1	58.3	95.1	83.1	46.9	79.0	73.9	69.8
MiniCPM-V-2	2.8B	55.6	71.9	62.9	-	80.7	86.3	38.2	64.1	67.1	-
Vintern-3B-beta	3.7B	68.3	-	69.1	-	75.0	87.4	46.7	70.6	70.0	-
Llama 3.2 11B	11B	83.4	88.4	91.1	-	-	-	50.7	68.0	-	-
Qwen2-VL-72B	73B	88.3	96.5	88.1	84.5	91.2	87.2	64.5	86.9	77.9	85.0
GPT-4o	-	85.7	92.8	84.7	-	90.1	97.2	69.1	82.1	76.7	-
InternVL2-V2PE-32K	2.0B	76.4	83.9	73.2	55.9	94.9	88.8	36.6	73.5	71.2	72.5

Long-Context MLLM Benchmarks

Model	#Param	MM-NIAH/Image	MM-NIAH/Text	MM-NIAH/Avg	Milebench/T	Milebench/S	Milebench/NI	Milebench/Avg	VideoMME	MVBench
InternVL2-2B	2.0B	23.0	18.9	21.0	58.2	54.5	37.0	49.9	-	-
Phi-3-Vision	2.7B	-	-	-	46.9	50.0	-	-	-	-
OmChat	3.9B	-	-	-	51.4	52.0	-	-	45.9	50.2
LongLLaVA	9B	-	-	-	47.3	46.8	-	-	43.7	49.1
LongLLaVA	13B	-	-	-	52.7	52.1	-	-	51.6	54.6
VILA	13B	14.5	40.5	27.5	-	-	-	-	-	-
Gemini-1.5	-	28.5	82.1	55.2	50.2	58.3	97.9	68.8	69.6	-
GPT-4V	-	-	84.1	-	45.6	58.9	99.4	68.0	59.9	43.5
GPT-4o	-	-	-	-	56.2	63.5	-	-	64.7	-
Claude3-Opus	-	-	-	-	37.4	48.1	85.3	56.9	59.7	-
InternVL2-V2PE-32K	2.0B	78.1	85.7	81.8	65.5	56.4	97.2	72.5	50.7	65.6

Usage

Please refer to our GitHub Repo.

License

This project is released under the MIT License.

Citation

If you find this work helpful in your research, please consider citing:

@misc{ge2024v2peimprovingmultimodallongcontext,
      title={V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding}, 
      author={Junqi Ge and Ziyi Chen and Jintao Lin and Jinguo Zhu and Xihui Liu and Jifeng Dai and Xizhou Zhu},
      year={2024},
      eprint={2412.09616},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.09616}, 
}