The absolute trainer to light up AI agents.

Agentic AI - Multi-Agent DEMO using AWS Strands Agents/Bedrock, and MCP. Features A2A communication, Planner-Executor patterns, and intelligent report generation.

Repo for DeepFin Tutorial Series

Zork I (Microcomputer Version) by Infocom

AWS Presentation script generator specialized for AWS Service Introduction Deck (pptx)

Implement a reasoning LLM in PyTorch from scratch, step by step

Kernels & AI inference engine for mobile devices.

State-of-the-art TTS model under 25MB 😻

Video Download to nas 의 크롬 엣지 확장 프로그램입니다.

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

de-pixelate youtube video gaV-O6NPWrI

Amazon Bedrock의 LLM을 활용하여 PPTX 슬라이드 내 텍스트를 지정한 언어로 번역 합니다.

A TTS model capable of generating ultra-realistic dialogue in one pass.

It shows a bedrock agent.

It shows how to realize agentic RAG.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

This Guidance shows how to handle sudden traffic spikes in Amazon Aurora using a mixed-configuration architecture that combines a provisioned Aurora cluster with Aurora Serverless v2 instances and …

This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be …

Training LLMs with QLoRA + FSDP

Lane identification system for camera based systems.

Educational materials on deep learning by Weights & Biases

We write your reusable computer vision tools. 💜

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

This is the official implementation of "Blind Image Restoration via Fast Diffusion Inversion"

This hands-on walks you through fine-tuning an open source LLM on Azure and serving the fine-tuned model on Azure. It is intended for Data Scientists and ML engineers who have experience with fine-…

Every practical and proposed defense against prompt injection.

data-to-paper: Backward-traceable AI-driven scientific research