Are Bigger Encoders Always Better in Vision Large Models?
- URL: http://arxiv.org/abs/2408.00620v1
- Date: Thu, 1 Aug 2024 15:05:42 GMT
- Title: Are Bigger Encoders Always Better in Vision Large Models?
- Authors: Bozhou Li, Hao Liang, Zimo Meng, Wentao Zhang,
- Abstract summary: multimodal large language models (MLLMs) have shown strong potential in real-world applications.
The scaling trend of vision language models (VLMs) under the current mainstream paradigm has not been extensively studied.
We conduct experiments on the pretraining stage of MLLMs using different encoder sizes and large language model (LLM) sizes.
- Score: 21.797332686137203
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In recent years, multimodal large language models (MLLMs) have shown strong potential in real-world applications. They are developing rapidly due to their remarkable ability to comprehend multimodal information and their inherent powerful cognitive and reasoning capabilities. Among MLLMs, vision language models (VLM) stand out for their ability to understand vision information. However, the scaling trend of VLMs under the current mainstream paradigm has not been extensively studied. Whether we can achieve better performance by training even larger models is still unclear. To address this issue, we conducted experiments on the pretraining stage of MLLMs. We conduct our experiment using different encoder sizes and large language model (LLM) sizes. Our findings indicate that merely increasing the size of encoders does not necessarily enhance the performance of VLMs. Moreover, we analyzed the effects of LLM backbone parameter size and data quality on the pretraining outcomes. Additionally, we explored the differences in scaling laws between LLMs and VLMs.
Related papers
- InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling [56.130911402831906]
This paper aims to improve the performance of video large language models (LM) via long and rich context (LRC) modeling.
We develop a new version of InternVideo2.5 with focus on enhancing the original MLLMs' ability to perceive fine-grained details in videos.
Experimental results demonstrate this unique designML LRC greatly improves the results of video MLLM in mainstream understanding benchmarks.
arXiv Detail & Related papers (2025-01-21T18:59:00Z) - DriVLM: Domain Adaptation of Vision-Language Models in Autonomous Driving [20.644133177870852]
multimodal large language models (MLLM) can combine multiple modalities such as pictures, videos, sounds, texts, etc.
Most MLLMs require very high computational resources, which is a major challenge for most researchers and developers.
In this paper, we explored the utility of small-scale MLLMs and applied small-scale MLLMs to the field of autonomous driving.
arXiv Detail & Related papers (2025-01-09T09:02:41Z) - NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects? [19.525612393979777]
We introduce a novel benchmark, NEMO, which comprises 900 images of origiNal fruits and their corresponding attributE-MOdified ones.
We assess 26 recent open-sourced and commercial models using our benchmark.
The findings highlight pronounced performance gaps in recognizing objects in NEMO and reveal distinct answer preferences across different models.
arXiv Detail & Related papers (2024-11-26T17:47:34Z) - LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch.
Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process.
By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
arXiv Detail & Related papers (2024-07-28T06:10:47Z) - LM4LV: A Frozen Large Language Model for Low-level Vision Tasks [25.3601306724822]
$textbfLM4LV$ is a framework that enables a large language model to solve a range of low-level vision tasks without any multi-modal data or prior.
This showcases the LLM's strong potential in low-level vision and bridges the gap between MLLMs and low-level vision tasks.
arXiv Detail & Related papers (2024-05-24T17:25:00Z) - Dense Connector for MLLMs [89.50595155217108]
We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs.
Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens.
Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
arXiv Detail & Related papers (2024-05-22T16:25:03Z) - Efficient Multimodal Large Language Models: A Survey [60.7614299984182]
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning.
The extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry.
This survey provides a comprehensive and systematic review of the current state of efficient MLLMs.
arXiv Detail & Related papers (2024-05-17T12:37:10Z) - Efficient Multimodal Learning from Data-centric Perspective [21.35857180519653]
We introduce Bunny, a family of lightweight MLLMs with flexible vision and language backbones for efficient multimodal learning.
Experiments show that our Bunny-4B/8B outperforms the state-of-the-art large MLLMs on multiple benchmarks.
arXiv Detail & Related papers (2024-02-18T10:09:10Z) - Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored.
We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
arXiv Detail & Related papers (2023-12-26T07:24:46Z) - An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning [70.48605869773814]
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information.
This study empirically evaluates the forgetting phenomenon in large language models during continual instruction tuning.
arXiv Detail & Related papers (2023-08-17T02:53:23Z)
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.