LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Visual instruction tuning has made considerable strides in enhancing the capabilities of Large Multimodal Models (LMMs). However, existing open LMMs largely focus on single-image tasks, their applications to multi-image scenarios remains less explored. Additionally, prior LMM research separately tackles different scenarios, leaving it impossible to generalize cross scenarios with new emerging capabilities. To this end, we introduce LLaVA-NeXT-Interleave, which simultaneously tackles Multi-image, Multi-frame (video), Multi-view (3D), and Multi-patch (single-image) scenarios in LMMs. To enable these capabilities, we regard the interleaved data format as a general template and compile the M4-Instruct dataset with 1,177.6k samples, spanning 4 primary domains with 14 tasks and 41 datasets. We also curate the LLaVA-Interleave Bench to comprehensively evaluate the multi-image performance of LMMs. Through extensive experiments, LLaVA-NeXT-Interleave achieves leading results in multi-image, video, and 3D benchmarks, while maintaining the performance of single-image tasks. Besides, our model also exhibits several emerging capabilities, e.g., transferring tasks across different settings and modalities. Code is available at https://github.com/LLaVA-VL/LLaVA-NeXT
Code (3)
Tasks
Video Question AnsweringZero-Shot Video Question AnswerMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Quizzard@INOVA Challenge 2025 -- Track A: Plug-and-Play Technique in Interleaved Multi-Image Model
This paper addresses two main objectives. Firstly, we demonstrate the impressive performance of the LLaVA-NeXT-interleave on 22 datasets across three different tasks: Multi-Image Reasoning, Documents and Knowledge-Based …
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
This paper introduces MVLLaVA, an intelligent agent designed for novel view synthesis tasks. MVLLaVA integrates multiple multi-view diffusion models with a large multimodal model, LLaVA, enabling it to handle a wide rang…
DescriptiveNovel View SynthesisConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating exc…
Visual Question AnsweringLLaVA-OneVision: Easy Visual Task Transfer
We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results de…
3D Question Answering (3D-QA)Multiple-choiceTemporal Relation Extraction+6MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting
While Large Language Models (LLMs) can achieve human-level performance in various tasks, they continue to face challenges when it comes to effectively tackling multi-step physics reasoning tasks. To identify the shortcom…
Question Answering