paper-with-me

홈 › Papers

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

2023-11-09 · Shilong Liu, Hao Cheng, Haotian Liu, Hao Zhang, Feng Li, Tianhe Ren, Xueyan Zou, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang, Jianfeng Gao, Chunyuan Li

LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-language models and can activate relevant tools based on users' inputs to fulfill real-world tasks. LLaVA-Plus is trained on multimodal instruction-following data to acquire the ability to use tools, covering visual understanding, generation, external knowledge retrieval, and compositions. Empirical results show that LLaVA-Plus outperforms LLaVA in existing capabilities and exhibits new ones. It is distinct in that the image query is directly grounded and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios.

📄 PDF Abstract BibTeX arXiv:2311.05437

Code (1)

LLaVA-VL/LLaVA-Plus-Codebase 공식 구현 pytorch

Tasks

Instruction FollowingLLM real-life tasksLMM real-life tasksRetrievalVisual Question Answering

Similar Papers 제목 키워드 기반

LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models

2026-01-28 · Pengcheng Zheng, Chaoning Zhang, Jiarong Mo, GuoHui Li 외 arxiv

Large multimodal models (LMMs) have achieved impressive performance on various vision-language tasks, but their substantial computational and memory costs hinder their practical deployment. Existing compression methods o…

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

2024-06-25 · Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu 외

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing lim…

DiversityMathMathematical Problem-SolvingMathematical Reasoning

Video Instruction Tuning With Synthetic Data

2024-10-03 · Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li 외

The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating…

3D Question Answering (3D-QA)Instruction FollowingMultiple-choice+5

MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents

2025-08-29 · Xijia Tao, Yihua Teng, Xinxing Su, Xinyu Fu 외 arxiv

Existing multimodal browsing benchmarks often fail to require genuine multimodal reasoning, as many tasks can be solved with text-only heuristics without vision-in-the-loop verification. We introduce MMSearch-Plus, a 311…

Multimodal ReasoningText Retrieval

LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models

2025-09-30 · Guolei Huang, Qinzhi Peng, Gan Xu, Yao Huang 외 arxiv

As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety concerns intensify for multimodal multi-turn dialogue, which is characterized by concealment of malicious intent, contextual risk accumulatio…

Red Teaming