paper-with-me

홈 › Papers

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

2025-03-24 · Ruichuan An, Sihan Yang, Ming Lu, Renrui Zhang, Kai Zeng, Yulin Luo, Jiajun Cao, Hao Liang, Ying Chen, Qi She, Shanghang Zhang, Wentao Zhang

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts. However, they mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes the first multi-concept personalization paradigm, MC-LLaVA. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the costs related to joint training, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location confidence maps for enhanced recognition and grounding capabilities. To advance multi-concept personalization research, we further contribute a high-quality instruction tuning dataset. We carefully collect images with multiple characters and objects from movies and manually generate question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive qualitative and quantitative experiments demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at $\href{https://github.com/arctanxarc/MC-LLaVA}{https://github.com/arctanxarc/MC-LLaVA}$.

📄 PDF Abstract BibTeX arXiv:2503.18854

Code (1)

arctanxarc/mc-llava 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingQuestion AnsweringVisual Question Answering

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

2024-11-18 · Ruichuan An, Sihan Yang, Ming Lu, Renrui Zhang 외

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-prov…

Language ModelingLanguage ModellingQuestion AnsweringVisual Question Answering

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant

2025-05-06 · Yifan Xiang, Zhenxi Zhang, Bin Li, Yixuan Weng 외

Recent advances in personalized MLLMs enable effective capture of user-specific concepts, supporting both recognition of personalized concepts and contextual captioning. However, humans typically explore and reason over …

DescriptiveMultiple-choiceRelational Reasoning

Yo'LLaVA: Your Personalized Language and Vision Assistant

2024-06-13 · Thao Nguyen, Haotian Liu, Yuheng Li, Mu Cai 외

Large Multimodal Models (LMMs) have shown remarkable capabilities across a variety of tasks (e.g., image captioning, visual question answering). While broad, their knowledge remains generic (e.g., recognizing a dog), and…

Image CaptioningQuestion AnsweringVisual Question Answering

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

2025-09-28 · Xiang An, Yin Xie, Kaicheng Yang, Wenkang Zhang 외 arxiv

We present LLaVA-OneVision-1.5, a novel family of Large Multimodal Models (LMMs) that achieve state-of-the-art performance with significantly reduced computational and financial costs. Different from the existing works, …

Multimodal Reasoning

MyVLM: Personalizing VLMs for User-Specific Queries

2024-03-21 · Yuval Alaluf, Elad Richardson, Sergey Tulyakov, Kfir Aberman 외

Recent large-scale vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and generating textual descriptions for visual content. However, these models lack an understanding of user-spec…

Image CaptioningLanguage ModellingQuestion AnsweringVisual Question Answering