MoExtend: Tuning New Experts for Modality and Task Extension
- URL: http://arxiv.org/abs/2408.03511v1
- Date: Wed, 7 Aug 2024 02:28:37 GMT
- Title: MoExtend: Tuning New Experts for Modality and Task Extension
- Authors: Shanshan Zhong, Shanghua Gao, Zhongzhan Huang, Wushao Wen, Marinka Zitnik, Pan Zhou,
- Abstract summary: 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.
- Score: 61.29100693866109
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) excel in various tasks but are primarily trained on text data, limiting their application scope. Expanding LLM capabilities to include vision-language understanding is vital, yet training them on multimodal data from scratch is challenging and costly. Existing instruction tuning methods, e.g., LLAVA, often connects a pretrained CLIP vision encoder and LLMs via fully fine-tuning LLMs to bridge the modality gap. However, full fine-tuning is plagued by catastrophic forgetting, i.e., forgetting previous knowledge, and high training costs particularly in the era of increasing tasks and modalities. To solve this issue, we introduce MoExtend, 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 such as MoE and vision encoders. This approach enables rapid adaptation and extension to new modal data or tasks, effectively addressing the challenge of accommodating new modalities within LLMs. Furthermore, MoExtend avoids tuning pretrained models, thus mitigating the risk of catastrophic forgetting. Experimental results demonstrate the efficacy and efficiency of MoExtend in enhancing the multimodal capabilities of LLMs, contributing to advancements in multimodal AI research. Code: https://github.com/zhongshsh/MoExtend.
Related papers
- LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities.
We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities.
PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
arXiv Detail & Related papers (2024-10-26T13:19:57Z) - 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) - ModalPrompt:Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models [40.7613157799378]
Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed datasets jointly.
Existing methods leverage data replay or model expansion, both of which are not specially developed for LMMs.
We propose a novel dual-modality guided prompt learning framework (ModalPrompt) tailored for multimodal continual learning.
arXiv Detail & Related papers (2024-10-08T09:35:37Z) - 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) - From Static to Dynamic: A Continual Learning Framework for Large
Language Models [41.59643329735528]
This paper presents DynaMind, a novel continual learning framework for large language models (LLMs)
DynaMind incorporates memory mechanisms to assimilate new knowledge and modular operators to enhance the model inference process.
Benchmark experiments demonstrate DynaMind's effectiveness in overcoming these challenges.
arXiv Detail & Related papers (2023-10-22T10:18:53Z) - Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large
Language Models [77.2078051555533]
We propose a novel and affordable solution for the effective VL adaption of large language models (LLMs)
Instead of using large neural networks to connect the image encoder and LLM, MMA adopts lightweight modules, i.e., adapters.
MMA is also equipped with a routing algorithm to help LLMs achieve an automatic shift between single- and multi-modal instructions.
arXiv Detail & Related papers (2023-05-24T11:06:15Z) - eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception.
Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency.
We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
arXiv Detail & Related papers (2023-03-20T19:20:34Z)
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.