Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

• URL: http://arxiv.org/abs/2410.08202v1
• Date: Thu, 10 Oct 2024 17:59:22 GMT
• Title: Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
• Authors: Gen Luo, Xue Yang, Wenhan Dou, Zhaokai Wang, Jifeng Dai, Yu Qiao, Xizhou Zhu,
• Abstract summary: We present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of visual experts via a multimodal mixture-of-experts structure. We also propose an innovative pre-training strategy to maximize the visual capability of Mono-InternVL, namely Endogenous Visual Pre-training (EViP)
• Score: 49.407311947143825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of Large Language Models (LLMs) has led to an influx of efforts to extend their capabilities to multimodal tasks. Among them, growing attention has been focused on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. Despite the structural simplicity and deployment-friendliness, training a monolithic MLLM with promising performance still remains challenging. In particular, the popular approaches adopt continuous pre-training to extend a pre-trained LLM to a monolithic MLLM, which suffers from catastrophic forgetting and leads to performance degeneration. In this paper, we aim to overcome this limitation from the perspective of delta tuning. Specifically, our core idea is to embed visual parameters into a pre-trained LLM, thereby incrementally learning visual knowledge from massive data via delta tuning, i.e., freezing the LLM when optimizing the visual parameters. Based on this principle, we present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of visual experts via a multimodal mixture-of-experts structure. Moreover, we propose an innovative pre-training strategy to maximize the visual capability of Mono-InternVL, namely Endogenous Visual Pre-training (EViP). In particular, EViP is designed as a progressive learning process for visual experts, which aims to fully exploit the visual knowledge from noisy data to high-quality data. To validate our approach, we conduct extensive experiments on 16 benchmarks. Experimental results not only validate the superior performance of Mono-InternVL compared to the state-of-the-art MLLM on 6 multimodal benchmarks, e.g., +113 points over InternVL-1.5 on OCRBench, but also confirm its better deployment efficiency, with first token latency reduced by up to 67%.

Related papers

• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs [40.74693126923826]
  Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. Training adapters with image-level supervision often results in significant misalignment. We introduce Supervised Embedding Alignment (SEA), a token-level alignment method that leverages vision-language pre-trained models.
  arXiv  Detail & Related papers  (2024-08-21T17:58:02Z)
• MoExtend: Tuning New Experts for Modality and Task Extension [61.29100693866109]
  MoExtend is an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models.
  arXiv  Detail & Related papers  (2024-08-07T02:28:37Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [56.391404083287235]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• MoE-LLaVA: Mixture of Experts for Large Vision-Language Models [27.930351465266515]
  We propose a simple yet effective training strategy MoE-Tuning for LVLMs. MoE-LLaVA, a MoE-based sparse LVLM architecture, uniquely activates only the top-k experts through routers. Experiments show the significant performance of MoE-LLaVA in a variety of visual understanding and object hallucination benchmarks.
  arXiv  Detail & Related papers  (2024-01-29T08:13:40Z)
• u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
  u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
  arXiv  Detail & Related papers  (2023-11-09T13:18:27Z)

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.