SkalskiP / SoMLinks
Unofficial implementation and experiments related to Set-of-Mark (SoM) 👁️
☆88Updated 2 years ago
Alternatives and similar repositories for SoM
Users that are interested in SoM are comparing it to the libraries listed below
Sorting:
- Testing and evaluating the capabilities of Vision-Language models (PaliGemma) in performing computer vision tasks such as object detectio…☆84Updated last year
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆37Updated 2 years ago
- Finetune any model on HF in less than 30 seconds☆56Updated last month
- The Next Generation Multi-Modality Superintelligence☆70Updated last year
- Enhancement in Multimodal Representation Learning.☆40Updated last year
- EdgeSAM model for use with Autodistill.☆29Updated last year
- Visual RAG using less than 300 lines of code.☆29Updated last year
- Cerule - A Tiny Mighty Vision Model☆68Updated 3 weeks ago
- Summarize any Arixv Paper with ease☆66Updated 2 years ago
- ☆63Updated last year
- ☆69Updated last year
- An automated tool for discovering insights from research papaer corpora☆137Updated last year
- Extract information, summarize, ask questions, and search videos using OpenAI's Vision API 🚀🎦☆62Updated 2 years ago
- ☆54Updated last year
- A framework to enable multimodal models to play games on a computer.☆97Updated last year
- Maybe the new state of the art vision model? we'll see 🤷♂️☆167Updated last year
- Use Florence 2 to auto-label data for use in training fine-tuned object detection models.☆67Updated last year
- run paligemma in real time☆133Updated last year
- ☆29Updated 2 years ago
- ☆86Updated last year
- Streamlit app presented to the Streamlit LLMs Hackathon September 23☆16Updated last year
- A real-time video caption to conversation bot that captures frames generates captions and creates conversational responses using a Large …☆122Updated 2 years ago
- ☆35Updated 2 years ago
- (WACV 2025 - Oral) Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, H…☆84Updated 4 months ago
- Backtracing: Retrieving the Cause of the Query, EACL 2024 Long Paper, Findings.☆91Updated last year
- ☆59Updated last year
- Use Grounding DINO, Segment Anything, and GPT-4V to label images with segmentation masks for use in training smaller, fine-tuned models.☆65Updated 2 years ago
- Official implementation of "Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models"☆37Updated last year
- Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta☆16Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated last year