Skip to main content

Vision-Language Models

Explore machine learning papers and reviews related to Vision-Language Models. Find insights, analysis, and implementation details.

  • Tagged with
  • 10 papers
Back to all papers

Papers Related to Vision-Language Models

ECCV 2024

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Shilong Liu, Zhaoyang Zeng, +10

Trace Grounding DINO through text-image enhancement, language-guided anchors, cross-modal decoding and phrase grounding, with Python and evaluation caveats.

2025

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Michael Tschannen, Alexey Gritsenko, +12

Explore SigLIP 2 through decoder supervision, EMA teachers, masked features and NaFlex geometry, with runnable CPU mechanics and recorded image-text matching.

ICML 2021

ALIGN: Scaling Vision-Language Learning with Noisy Text Supervision

Chao Jia, Yinfei Yang, +8

How ALIGN scales vision-language pre-training to 1.8 billion noisy image-alt-text pairs, showing that the sheer scale of a raw, uncurated dataset can outweigh careful data cleaning for a simple dual-encoder contrastive model.

TMLR 2022

CoCa: Contrastive Captioners are Image-Text Foundation Models

Jiahui Yu, Zirui Wang, +4

How CoCa trains a single image-text foundation model with both a contrastive loss and a generative captioning loss by splitting the text decoder into unimodal and multimodal halves, computed in one forward pass.

NeurIPS 2022

Flamingo: a Visual Language Model for Few-Shot Learning

Jean-Baptiste Alayrac, Jeff Donahue, +25

How Flamingo bridges a frozen vision encoder and a frozen language model with a Perceiver Resampler and gated cross-attention layers, enabling few-shot learning from interleaved image-text sequences.

arXiv 2024

Qwen2-VL: Vision-Language Perception at Any Resolution

Peng Wang, Shuai Bai, +17

How Qwen2-VL perceives images and video at any resolution with naive dynamic resolution (variable visual tokens) and M-RoPE, a multimodal rotary position embedding that decomposes position into temporal, height, and width components.

ICCV 2023

SigLIP: Sigmoid Loss for Language Image Pre-Training

Xiaohua Zhai, Basil Mustafa, +2

How SigLIP replaces CLIP’s softmax contrastive loss with a pairwise sigmoid loss, removing the global softmax denominator and enabling chunked all-pairs computation and strong language-image pre-training at smaller batch sizes.

Mastodon