Pith. sign in

REVIEW 16 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.CLcs.CV
keywords mplugcross-modalvision-languagetasksvisualdownstreameffectiveefficient
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios

    cs.LG 2024-11 conditional novelty 7.0 of 10

    A new attention-based reasoning module combining iterative steps with parallel operation slots improves accuracy on multiple visual question answering benchmarks while staying lightweight and partially interpretable.

  2. Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Lavida-O introduces an elastic mixture-of-transformers architecture that brings high-resolution text-to-image generation, object grounding, and image editing into a single masked diffusion model, using planning and se...

  3. INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

    cs.CV 2025-07 conditional novelty 6.0 of 10

    INTER is a training-free logit-correction method that adds Harsanyi interaction scores to selected keyword tokens, lowering hallucination on six LVLM benchmarks.

  4. GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A multi-agent vision-language framework that extracts event, time, and location from public event images, evaluated with a new soft metric on VLM-augmented datasets.

  5. DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Introduces DetailMaster, a 4,116-prompt benchmark with fine-grained evaluation of long-prompt text-to-image generation, finding that state-of-the-art models achieve only about 50% accuracy on attribute binding and spa...

  6. Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation

    cs.CV 2025-04 conditional novelty 6.0 of 10

    MR-PLIP is a multi-resolution pathology vision-language model that aligns histology patches and generated text across 5x, 10x, 20x, and 40x magnifications and reports improved transfer to 26 downstream pathology benchmarks.

  7. PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction

    cs.CV 2025-01 reject novelty 6.0 of 10

    PuzzleGPT, a zero-shot expert pipeline, reports state-of-the-art scores on TARA and WikiTilo time and location prediction, though the evaluation uses different metrics for the proposed method and baselines.

  8. Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Pix2Cap-COCO provides 167,254 pixel-aligned instance captions for COCO images and introduces panoptic segmentation-captioning as a benchmark task.

  9. Improving Image Captioning by Mimicking Human Reformulation Feedback at Inference-time

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A reformulation model trained on human caption edits improves image captioning at inference time, yielding strong results on German captions and style transfer.

  10. Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Aligning cross-attention map similarity to text self-attention maps at test time improves semantic alignment in Stable Diffusion for prompts with multiple objects and attributes.

  11. Multimodal Feature Fusion Network with Text Difference Enhancement for Remote Sensing Change Detection

    cs.CV 2025-09 conditional novelty 5.0 of 10

    MMChange fuses image features with VLM-generated text descriptions of bitemporal remote sensing images, reporting state-of-the-art IoU/F1 on LEVIR-CD, WHU-CD, and SYSU-CD.

  12. Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

    cs.CV 2025-05 reject novelty 5.0 of 10

    Selftok encodes images as diffusion-time-indexed discrete tokens, enabling a pure autoregressive VLM and visual RL with strong GenEval and DPG scores, though its claim that spatial tokens cannot support RL is not proven.

  13. ReFrame: Rectification Framework for Image Explaining Architectures

    cs.CV 2025-06 reject novelty 4.0 of 10

    ReFrame wraps image captioning, VQA, and GPT-4 with a Mask R-CNN rectifier, reporting big gains on metrics defined against that same detector.

  14. Explainability for Vision Foundation Models: A Survey

    cs.CV 2025-01 conditional novelty 4.0 of 10

    A structured review of 122 papers on explainability for vision foundation models, with a taxonomy and the finding that quantitative evaluation is rare (36%).

  15. Visual question answering: from early developments to recent advances -- a survey

    cs.CV 2025-01 conditional novelty 2.0 of 10

    A survey that classifies VQA architectures by encoder, fusion, and decoder, reviews datasets and metrics, and discusses applications and future directions.

  16. Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges

    cs.LG 2024-12 conditional

    A broad but error-prone survey of LLM and MLLM architectures, training methods, benchmarks, and challenges.

Pith tools