paper-with-me

Papers

Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

2023-08-25 · Chi Chen, Ruoyu Qin, Fuwen Luo, Xiaoyue Mi, Peng Li, Maosong Sun, Yang Liu

Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment. In this paper, we propose Position-enhanced Visual Instruction Tuning (PVIT), which extends the functionality of MLLMs by integrating an additional region-level vision encoder. This integration promotes a more detailed comprehension of images for the MLLM. In addition, to efficiently achieve a fine-grained alignment between the vision modules and the LLM, we design multiple data generation strategies to construct an image-region-language instruction dataset. Finally, we present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model. Code and data will be released at https://github.com/PVIT-official/PVIT.

📄 PDF Abstract BibTeX arXiv:2308.13437

Code (1)

pvit-official/pvit 공식 구현 pytorch

Tasks

cross-modal alignmentPosition

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction

2024-02-06 · Yonggang Jin, Ge Zhang, Hao Zhao, Tianyu Zheng 외

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios …

JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation

2026-05-05 · Lin Song, Wenbo Li, Guoqing Ma, Wei Tang 외 arxiv

We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language M…

Text-to-Image GenerationImage Editing

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

2023-08-20 · Yanda Li, Chi Zhang, Gang Yu, Zhibin Wang 외

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to ali…

Visual Question Answering

Visual Instruction Tuning

2023-04-17 · NeurIPS 2023 11 · Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, w…

1 Image, 2*2 Stitching3D Question Answering (3D-QA)Image ClassificationImage Retrieval+9

MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models

2024-11-15 · Jianhong Tu, Zhuohao Ni, Nicholas Crispino, Zihao Yu 외

We present a novel instruction tuning recipe to improve the zero-shot task generalization of multimodal large language models. In contrast to existing instruction tuning mechanisms that heavily rely on visual instruction…

Instruction FollowingZero-shot Generalization