🤖 Advanced Privacy Browser Core with Unified Fingerprint Defense: Cloudflare, Akamai, Kasada, Shape, DataDome, PerimeterX, hCaptcha, FunCaptcha, Imperva, reCAPTCHA, ThreatMetrix, Adscore

Fully open reproduction of DeepSeek-R1

Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Faster Whisper for Home Assistant - custom integration with a local Speech-to-Text engine

🤖 Build voice-based LLM agents. Modular + open source.

Code release for "Learning Video Representations from Large Language Models"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

ImageBind One Embedding Space to Bind Them All

[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

This is an implementation of zero-shot instance segmentation using Segment Anything.

[Pattern Recognition 25] CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

This repository contains the dataset and the pytorch implementations of the models from the paper CIDER: Commonsense Inference for Dialogue Explanation and Reasoning. CIDER has been accepted to app…

You can do anything by sota AI with prompt ,auto AI tools , VL larger model fine and project

This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.

Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena

Official Code for DragGAN (SIGGRAPH 2023)

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Using Color Histogram, SVD and Dynamic Clustering Method obtained Key-Frames from a video. This analysis can be used to identify frames which make a shot. The code is well documented.

Video Key Frame Extraction Using Local Descriptors Based on Deep Learning Method(Superpoint)

This data set contains accelerometer and gyroscope recordings from over 200 participants performing various gym exercises. This data set is described in more detail in the associated manuscript: Mo…

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

RED Teams SUITS submission for the 22-23 SUITS challenge.

Code for "Generalizable deep learning model for early Alzheimer’s disease detection from structural MRIs"

Large-scale pretrained models for goal-directed dialog