paper-with-me

Papers

VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

2021-11-03 · Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Furu Wei

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA, NLVR2 and image-text retrieval. The code and pretrained models are available at https://aka.ms/vlmo.

📄 PDF Abstract BibTeX arXiv:2111.02358

Code (2)

microsoft/unilm/tree/master/vlmo 공식 구현 pytorch
ylsung/vl-merging pytorch

Tasks

Image RetrievalImage-text RetrievalRetrievalText RetrievalVisual Question Answering (VQA)Visual Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
VLMo VLMo is a unified vision-language pre-trained model that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. A Mixture-of-Modality-Experts…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

2025-04-29 · Amaan Izhar, Nurul Japar, Norisma Idris, Ting Dang

Medical image reporting (MIR) aims to generate structured clinical descriptions from radiological images. Existing methods struggle with fine-grained feature extraction, multimodal alignment, and generalization across di…

cross-modal alignmentDecoderImage CaptioningMixture-of-Experts

ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation

2025-05-28 · Jiawen Yu, Hairuo Liu, Qiaojun Yu, Jieji Ren 외

Vision-Language-Action (VLA) models have advanced general-purpose robotic manipulation by leveraging pretrained visual and linguistic representations. However, they struggle with contact-rich tasks that require fine-grai…

Contact-rich ManipulationMixture-of-ExpertsVision-Language-Action

Efficient, VRAM-Constrained xLM Inference on Clients

2026-04-29 · Aditya Ukarande, Deep Shekhar, Marc Blackstein, Ram Rangan arxiv

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as …

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE

2023-08-23 · Junyi Chen, Longteng Guo, Jia Sun, Shuai Shao 외

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multi…

Image-text matchingImage-text RetrievalMixture-of-ExpertsQuestion Answering+5

Beyond Language Modeling: An Exploration of Multimodal Pretraining

2026-03-03 · Shengbang Tong, David Fan, John Nguyen, Ellis Brown 외 arxiv

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clar…