Papers › Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models...

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

10 Oct 2024CVPR 2025 1arXiv:2410.08202archive 2025-07-28

Gen Luo, Xue Yang, Wenhan Dou, Zhaokai Wang, Jiawen Liu, Jifeng Dai, Yu Qiao, Xizhou Zhu

In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for monolithic MLLMs often suffer from unstable optimization or catastrophic forgetting. To address this issue, our core idea is to embed a new visual parameter space into a pre-trained LLM, thereby stably learning visual knowledge from noisy data while freezing the LLM. 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 confirm the superior performance of Mono-InternVL than existing monolithic MLLMs on 13 of 16 multimodal benchmarks, e.g., +80 points over Emu3 on OCRBench. Compared to the modular baseline, i.e., InternVL-1.5, Mono-InternVL still retains comparable multimodal performance while reducing up to 67% first token latency. Code and model are released at https://huggingface.co/OpenGVLab/Mono-InternVL-2B.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Mixture-of-ExpertsVisual Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet Mono-InternVL-2B GPT-4 score 40.1 #112 of 231 Archive leaderboard report
Visual Question Answering MM-Vet Mono-InternVL-2B Params 2B #112 of 231 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

FocusSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections