OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3
-
Updated
Feb 21, 2026 - Python
#
vision-foundation-model
Here are 19 public repositories matching this topic...
A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explore how LMMs represent, transform, and align multimodal information internally.
generative-model generative paperlist vision-models large-language-models mechanistic-interpretability large-vision-language-models large-multimodal-models vision-foundation-model
-
Updated
Mar 4, 2026
Recognize Any Regions
open-world object-detection zero-shot instance-segmentation auto-labeling vision-language-pretraining open-vocabulary vision-language-model multimodal-representation-learning vision-foundation-model vision-language-foundation-model
-
Updated
Dec 18, 2024 - Python
[--branch main] FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning (CVPR25) [--branch FSVFM-extension] Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection (Extented Version)
face-antispoofing self-supervised-learning deepfake-detection vision-foundation-model ai-diffusion-generated-face-detection
-
Updated
Oct 20, 2025 - Python
[ICLR 2026] FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
-
Updated
Mar 11, 2026 - Python
A Vision Foundation Model for Cine Cardiac Magnetic Resonance Imaging
-
Updated
Mar 26, 2026 - Python
One-Shot Open Affordance Learning with Foundation Models (CVPR 2024)
-
Updated
Jul 30, 2024 - Python
Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"
-
Updated
Apr 3, 2025 - Python
MonoDINO-DETR: Depth-Enhanced Monocular 3D Object Detection Using a Vision Foundation Model
-
Updated
May 27, 2025 - Python
-
Updated
Jul 18, 2025 - Python
This repo collects some latest research work of Generative AI. It provides simple implementations to understand the ideas and some follow-up discussions to inspire future work.
-
Updated
Apr 24, 2025 - Python
Implementation of CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation.
computer-vision knowledge-distillation instance-segmentation semi-supervised contrastive-learning dense-contrastive-learning grounding-dino vision-foundation-model sam2 semi-supervised-knowledge-distillation
-
Updated
Jun 9, 2025
"Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model"
-
Updated
Jul 21, 2025 - Python
Codebase for probing VFMs and Feature Upsamplers using Intractive Segmentation.
-
Updated
May 9, 2025 - Python
A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
-
Updated
Mar 13, 2026 - Python
Simple Gradio application integrated with Hugging Face Multimodals to support visual question answering chatbot and more features
docker text-to-speech computer-vision gradio vlm visual-question-answering llm mllm vision-foundation-model image-text-to-text florence-2 xtts-v2 mini-internvl
-
Updated
Aug 16, 2024 - Python
A Training Objective for Interpretable Monosemantic Representations
sparse-autoencoders sparse-autoencoder fine-tuning explainable-ai mechanistic-interpretability vision-language-model vision-foundation-model vision-language-models vision-foundation-models
-
Updated
Feb 16, 2026 - Python
Florence-2 quick test
python tutorial jupyter-notebook image-captioning image-to-text colab-notebook visual-grounding referring-expression-comprehension huggingface-transformers multimodal-large-language-models vision-foundation-model florence-2
-
Updated
Aug 15, 2024 - Jupyter Notebook
ProRobo3D Benchmark to be release...
-
Updated
Feb 11, 2025
Improve this page
Add a description, image, and links to the vision-foundation-model topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vision-foundation-model topic, visit your repo's landing page and select "manage topics."