Pith

open record

sign in

arxiv: 2205.12005 · v2 · pith:KSYOKW2V · submitted 2022-05-24 · cs.CL · cs.CV

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:KSYOKW2Vrecord.jsonopen to challenge →

classification cs.CL cs.CV
keywords mplugcross-modalvision-languagetasksvisualdownstreameffectiveefficient
0
0 comments X
read the original abstract

Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from the problems of low computational efficiency and information asymmetry brought by the long visual sequence in cross-modal alignment. To address these problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections, which creates inter-layer shortcuts that skip a certain number of layers for time-consuming full self-attention on the vision side. mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability when directly transferred to multiple video-language tasks.

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. HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models

    cs.CV 2025-05 unverdicted novelty 7.0

    HyperCap is the first large-scale hyperspectral captioning dataset built from four benchmark HSI datasets using hybrid automated-manual annotations, with evaluations showing classification gains for vision-language models.

  2. The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding

    cs.CV 2024-12 unverdicted novelty 7.0

    CompART adds a composition loss on decomposed captions to regularize attention sums and improves multi-object grounding plus VQA across four VLM types and six benchmarks.

  3. ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

    cs.CV 2024-03 unverdicted novelty 7.0

    ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.

  4. StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback

    cs.CV 2025-10 conditional novelty 6.0

    StableSketcher improves text-to-sketch generation by fine-tuning a diffusion VAE and adding a VQA-based RL reward, while releasing the SketchDUO dataset of sketches with captions and QA pairs.

  5. VisChronos: Revolutionizing Image Captioning Through Real-Life Events

    cs.CV 2026-06 unverdicted novelty 5.0

    VisChronos is a framework that combines LLMs and dense captioning models to produce event-centric captions from single images, accompanied by the EventCap dataset.

  6. AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning

    cs.CV 2026-04 unverdicted novelty 5.0

    AeroRAG improves fine-grained aerial visual question answering by converting images to scene graphs and using retrieval-augmented generation to create compact LLM prompts.

  7. GIT: A Generative Image-to-text Transformer for Vision and Language

    cs.CV 2022-05 unverdicted novelty 5.0

    GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.

  8. OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

    cs.CV 2023-08 unverdicted novelty 4.0

    OpenFlamingo provides open-source autoregressive vision-language models that achieve 80-89% of Flamingo performance on seven vision-language datasets.