Stars
Soprano: Instant, Ultra-Realistic Text-to-Speech
Orient Anything V2, NeurIPS 2025 Spotlight
Standards for building agents, better
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
[ICCV 2025] Official Repository of VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges
🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.
[CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
Use Deepstream python API to extract the model output tensor and customize the post-processing of YOLO-Pose
yolov3, yolo12, dino, segmenations, face, pose, keypoints on deepstream
yolov8的车辆检测模型deepstream-python部署
Implementation of Nvidia DeepStream 7 with YOLOv9 Models.
Implementation of End-to-End YOLO Models for DeepStream
Meet Ava, the WhatsApp Agent
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
This is a repo for a number of examples using the smolagents framework from Hugging Face.
12 Lessons to Get Started Building AI Agents
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Official implementation of the paper "Watermarking Autoregressive Image Generation" (NeurIPS'25)
Computer vision project to predict football game detail from a single camera video clip
Anthropic's Interactive Prompt Engineering Tutorial
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
This repository contains LLM (Large language model) interview question asked in top companies like Google, Nvidia , Meta , Microsoft & fortune 500 companies.
KDebug is a Kubernetes debugging tool that allows you to interact with your Kubernetes clusters through LLMs. It uses the Model Control Protocol (MCP) to enable AI to execute Kubernetes commands on…
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.