pith. sign in

arxiv: 2405.16640 · v2 · pith:3D6QE4XHnew · submitted 2024-05-26 · 💻 cs.AI · cs.CL· cs.CV· cs.MM

A Survey of Multimodal Large Language Model from A Data-centric Perspective

classification 💻 cs.AI cs.CLcs.CVcs.MM
keywords mllmsdatalanguagelargemodelsmultimodalsurveydata-centric
0
0 comments X
read the original abstract

Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments. Data plays a pivotal role in the development and refinement of these models. In this survey, we comprehensively review the literature on MLLMs from a data-centric perspective. Specifically, we explore methods for preparing multimodal data during the pretraining and adaptation phases of MLLMs. Additionally, we analyze the evaluation methods for the datasets and review the benchmarks for evaluating MLLMs. Our survey also outlines potential future research directions. This work aims to provide researchers with a detailed understanding of the data-driven aspects of MLLMs, fostering further exploration and innovation in this field.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

    cs.CV 2026-05 unverdicted novelty 8.0

    TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.

  2. Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data

    cs.LG 2025-09 unverdicted novelty 7.0

    Introduces the first active learning framework for unaligned multimodal data that selects alignments using uncertainty and diversity to cut annotation costs by up to 40% on benchmarks while preserving accuracy.

  3. GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs

    cs.CL 2026-06 unverdicted novelty 6.0

    GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.

  4. All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding

    cs.CV 2026-04 unverdicted novelty 6.0

    A unified synthetic data generation pipeline produces unlimited annotated multimodal video data across multiple tasks, enabling models trained mostly on synthetic data to generalize effectively to real-world video und...

  5. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

    cs.CV 2026-04 unverdicted novelty 4.0

    OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.

  6. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.

  7. A Survey of Context Engineering for Large Language Models

    cs.CL 2025-07 accept novelty 4.0

    The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle...

  8. Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning

    cs.CL 2025-02 unverdicted novelty 2.0

    Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.