Machine Learning

Auto-generate viral YouTube Shorts!

Digitize your analog meters with AI!

LLM agents as your research pals!

Agentic RAG: AI agents for search.

ChatGLM3: Powering the future of AI.

Agentic AI workflows made easy.

Build Physical AI systems, faster.

DeepSeek-V3: MoE with 671B parameters.

DeepSeek-VL2: Advanced MoE Vision-Language.

Diffusion engine with many features.

Drag Your GAN: Edit images with points!

Drag Your GAN: Interactive editing!

LLM document intelligence tool.

LLMs for any ETL pipeline: FlashLearn.

AI-powered voice interviews for hiring.

Learn GPU coding interactively!

AI search with sources & citations.

Genesis: Ultra-fast embodied AI sim.

Detect & segment anything with text!

Unified Multimodal AI Models.

Build LLMs from scratch!

Fine-tune LLMs with ease and speed.

LLaVA: GPT-4 Vision Capabilities!

Lip-sync with diffusion models!

Learn ML by exploring world cultures!

AI-powered math animations.

MedRAX: AI agent for chest X-rays.

GPT-4o level MLLM on your phone!

GPT-4o level MLLM on your phone!

Vision-language understanding, evolved.

NanoSage 🧙: Your AI research buddy.

Text-to-Vector, redefined.

LLMs as image composers: Omost!

AI researcher that never stops.

Customize photos with any ID!

RL agents playing Pokemon Red!

High-quality video generation, fast!

Advanced AI Retrieval & Agentic RAG.

Automate data-driven R&D with RDAgent.

AI-powered resume tailor for jobs.

RouteLLM: Serve and evaluate LLMs.

AI-powered web scraping made easy.

GUI Agent & Computer Use Model.

Faster, cheaper, crisp image generation.

Real-time interactive generation.

Fast 3D models from a single image!

LLMs for web traversal benchmark.

Middleware for multi-LLM workflows.

Lyrics to full songs with YuE!

AI in Excel: Neural nets by hand!

Level up your AI engineering skills!

AI-powered side hustle guide.

Explore Amazon Bedrock with examples.

PyTorch Neural Nets, Simplified.

AI audio generation, now simple.

Fine-tune LLMs on your own hardware.

AI benchmark runtime framework.

AI agents controlling your browser!

Scaling Laws of Multi-Agent Systems

RAG pipelines made easy & hackable.

Open-source embedding database.

AI that plays Codenames really well.

NumPy/SciPy on GPU, made easy.

AI-powered data visualization.

Cloud Data Warehouse: Fast & Cheap.

AI-data warehouse for the unstructured

AI-powered iterative research.

Democratizing RL for LLMs.

Draw a UI, and get the HTML code!

Search, Scale, and Analyze Data.

AI-powered news, short & sweet.

Multilingual TTS with voice cloning!

Generate images with FLUX models.

Gemma: State-of-the-art LLMs.

Build GenAI apps: 21-lesson guide!

Video & 3D generation made easy.

Simulate human behavior with AI.

Autonomous web research agent.

Free multi-provider AI access.

Run Grok-1, a 314B parameter MoE model.

Local GRPO training: Feel the AHA! ✨

Model Serving Made Easy 🤖

Package, version, & share AI/ML.

Debug & Explain AI: See how it thinks.

LLM inference, optimized & easy.

Build AI apps visually with Langflow

Modular RAG system: Ask, Get, Done.

Hugging Face for real-world robotics.

Offline, ChatGPT-like chatbot.

Your guide to building with Llama.

Inference LLaMA in pure C/C++.

Inference Llama 2 in pure C.

Meta Llama 3: Accessible LLMs.

Llama3 from scratch, one tensor at a time.

LLM app data framework.

LLMs over structured/unstructured data.

AI agents for your Macbook.

Fine-tune multimodal models faster.

Animate images with Diffusion Model!

AI-powered fast file type detection.

Build agents with Model Context.

Memory layer for personalized AI.

User profile-based memory for GenAI.

MiniMind: Build a tiny LLM in 2 hrs!

Universal LLM deployment engine.

ML on Apple silicon, made simple.

Real-time recs with no collisions.

Stream Gemini with Multimodal Live API.

Academic OCR with LaTeX support.

Run large language models locally.

Run large language models locally.

AI-powered research, now with a UI!

Describe UI & see it rendered live.

Build state-of-art foundation models.

Chat with your data using PandaAI.

AI-powered document analysis & tagging.

Real-time data processing made easy.

Create autonomous digital beings.

KANs: MLPs with activations on edges.

Graph UI for AI Agents.

Fine-tune LLMs on a single GPU!

Your AI-powered Second Brain.

Reasoning-First Computer Control.

Deeper thoughts, better results!

RLHF: A work-in-progress textbook.

24/7 screen recording for AI apps.

Segment Anything: Masks for any object!

Generate 3D models from text!

AI-powered end-to-end testing.

Automate web tasks with LLMs!

AI-powered stock market insights.

Reusable computer vision tools.

AI agents surfing the web like humans.

Self-hosted AI coding assistant.

`tee` with a touch of 😂 and ✨.

Open-source Twitter's rec algo.

ML on the Web: Transformers, no server!

2x Faster Finetuning, 80% Less Memory!

Multilingual speech recognition magic.

ML speech recognition in your browser!

Real-time object detection evolved.

YOLOv9: Learn what you want to learn.