DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

• URL: http://arxiv.org/abs/2412.10302v1
• Date: Fri, 13 Dec 2024 17:37:48 GMT
• Title: DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• Authors: Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wang, Chong Ruan,
• Abstract summary: We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage DeepSeekMoE models with the Multi-head Latent Attention mechanism.
• Score: 39.14141055325595
• License:
• Abstract: We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage DeepSeekMoE models with the Multi-head Latent Attention mechanism, which compresses Key-Value cache into latent vectors, to enable efficient inference and high throughput. Trained on an improved vision-language dataset, DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models. Codes and pre-trained models are publicly accessible at https://github.com/deepseek-ai/DeepSeek-VL2.

Related papers

• LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer [109.61952368100756]
  We present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer. As a vision-language projector, Hiwin transformer comprises two primary modules. Extensive experiments demonstrate that LLaVA-UHD v2 achieves superior performance over existing MLLMs on popular benchmarks.
  arXiv  Detail & Related papers  (2024-12-18T14:07:46Z)
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling [128.24325909395188]
  We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0. InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
  arXiv  Detail & Related papers  (2024-12-06T18:57:08Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution [82.38677987249348]
  We present the Qwen2-VL Series, which redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos.
  arXiv  Detail & Related papers  (2024-09-18T17:59:32Z)
• DeepSeek-VL: Towards Real-World Vision-Language Understanding [24.57011093316788]
  We present DeepSeek-VL, an open-source Vision-Language (VL) Model for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse, scalable, and extensively covers real-world scenarios. We create a use case taxonomy from real user scenarios and construct an instruction tuning dataset.
  arXiv  Detail & Related papers  (2024-03-08T18:46:00Z)
• Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities [11.53488611812612]
  Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices. We introduce EdgeVL, a novel framework that seamlessly integrates dual-modality knowledge distillation and quantization-aware contrastive learning. Our work represents the first systematic effort to adapt large VL models for edge deployment, showcasing up to 15.4% accuracy improvements on multiple datasets and up to 93-fold reduction in model size.
  arXiv  Detail & Related papers  (2024-03-07T21:34:40Z)
• EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment [40.328294121805456]
  This work builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone.
  arXiv  Detail & Related papers  (2023-12-13T22:20:45Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.