Hugging Face - Videos
Back to Channel
How To Win Humanity's Last Hackathon - The hardest agent contest in AI.
Follow this org to sign up: https://hf-learn.short.gy/nvB8JD The hardest agent contest in AI just launched. Here's how to win it. You can now sign up to Humanity's Last Hackathon. You build Mac Me...
Multi-Agent AutoResearch with Open Source Models
In this video, we walk through a multi-agent setup of AutoResearch using open source models and OpenCode. Timestamps 00:00 - Introduction: Multi-agent AutoResearch setup 01:07 - Agent Roles: Resea...
RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source
Reinforcement learning is becoming central to agentic systems, but moving from RL for LLMs to RL for agents introduces a new set of challenges: environments, rollouts, tool use, inference bottlenec...
Hugging Face Journal Club: Embarrassingly Simple Self-Distillation Improves Code Generation
The Hugging Face research team discusses Apple's Embarrassingly Simple Self-Distillation Improves Code Generation paper. Paper: https://huggingface.co/papers/2604.01193
RoPE: Understanding Rotary Positional Embeddings in transformers
Mastering Rotary Positional Embeddings (RoPE): From Zero to Deep Dive Unlock the secrets behind modern Large Language Model (LLM) architectures in this comprehensive breakdown of Rotary Positional...
What are Mixture-of-Experts Models | ft. Aritra
In this clip, Aritra Roy Gosthipaty from the Hugging Face Transformers team breaks down one of the most important (and often misunderstood) architectures in modern AI: Mixture-of-Experts models. M...
Intro to Mixture of Experts | Aritra Roy Gosthipaty | HF Podcast #2
In this episode, Alejandro sits down with Aritra Roy Gosthipaty from the Hugging Face Transformers team to talk about mixture-of-experts models, why dense models still matter, how synthetic data ch...
Labs sharing their models via DropBox 😅
Local Agents are the Future
World Models in Plain English
We Hired 10 Humans to Train a Robot to Fold Shirts
hey everyone. here's a story about our robotics lab. 👉 Here is the blog: https://huggingface.co/spaces/lerobot/robot-folding
LlaVa in 90 seconds
Are World Models the Next Big Thing? | Merve Noyan
In this clip, Merve breaks down her predictions on ai for 2026 and explains why it matters in practice. Merve goes deep on world models, VLA systems, and on-device agentic models. Chapters: - 00:...
Introducing Storage Buckets
Hugging Face Buckets are a new storage primitive on the Hugging Face Hub for mutable ML artifacts like checkpoints, traces, logs, and pipeline outputs. In this video I explain where Buckets come fr...
How AI Vision Evolved | Merve Noyan
In this clip, Merve breaks down how AI vision evolved and explains why it matters in practice. Dense explanation of how vision evolved and why progress feels incremental now. 🤗 Listen to the full...
New Open Audio Models 🤗 | Recap with Jeff
This video covers the latest wave of open audio tooling, from Mistral's Voxtral 4B text-to-speech model to Cohere Transcribe for speech recognition and the Hugging Face infrastructure used to run l...
Transformers.js v4: State-of-the-art machine learning for the web
Transformers.js v4 is out! Read more about the release on: https://huggingface.co/blog/transformersjs-v4 Links: LFM2.5 1.2B Demo: https://huggingface.co/spaces/LiquidAI/LFM2.5-1.2B-Thinking-WebG...
Trackio Tutorial: Hugging Face's new, FREE experiment tracking library
A complete tutorial on how to install and get started with Trackio, a lightweight, free, and local-first experiment tracking library released by Hugging Face. For you and for your AI agents! Quick...
The Future of Vision in ML | Merve Noyan | HF Podcast #1
In this episode, we sit down with Merve to talk about where vision AI is heading: from early computer vision systems to modern multimodal models, world models, robotics, and open source AI. We dis...
Agentic Evaluations Workshop - Deep Dive on the Future on Evals for Agents.
As agents evolve from text conversations to autonomous agents capable of multi-step reasoning, tool use, and real-world task completion, evaluation methodologies must evolve to keep up. We will dis...
What is Hugging Face? - Models, Datasets & Spaces
Hugging Face can feel like "just a model website" when you first land on it, but it is a much bigger ecosystem. In this HF Universe walkthrough, I show how Models, Datasets, and Spaces fit together...
Teaching Tiny Models to Prove Hard Theorems | Lewis Tunstall | HF ML Club India EP1
About the speaker: Lewis Tunstall is a Machine Learning Engineer at Hugging Face, where he leads the research team's efforts to develop open-source tools and recipes for post-training LLMs. He's th...
Build a PyTorch ReLU Kernel with Hugging Face Kernels (CPU + Metal)
In this video, I walk through the Hugging Face Kernels Library and build a real PyTorch ReLU kernel end to end. You’ll see how to package kernels, publish compiled artifacts, and load the right ke...
How to use Claude Code to automate model training IN MINUTES
Can an AI agent act as a machine learning researcher? In this tutorial, I'll show you how to automate the training of AI models from scratch using AI agents, saving you time and computational costs...
From AI Agents to Faster Kernels: Ben Burtenshaw & Felix LeClair (AI Plumbers #2)
Felix LeClair sits down with Ben Burtenshaw from Hugging Face to discuss how the Hugging Face Kernels ecosystem makes high-performance kernels easier to build, share, and run. They cover agent-as...
Talk: Kernels Deep Dive (Ben Burtenshaw)
In this talk, Ben Burtenshaw from Hugging Face breaks down why optimized kernels are critical for real-world deep learning performance and how the Hugging Face Kernels ecosystem makes them easier t...
Benchmarking LLMs at the Game Of Science (Eleusis)
A card game ♠️♥️ to benchmark AI models at scientific discovery 🔬🧪 📝 Blog post : https://huggingface.co/spaces/huggingface/eleusis-benchmark 00:00 LLMs and science 01:55 The Eleusis Game 04:09 Our...
Hugging Face Journal Club: GLM-5: from Vibe Coding to Agentic Engineering
Recording of 19/02/2026, where the Hugging Face H4 team discusses "GLM-5: from Vibe Coding to Agentic Engineering". This is the technical report of https://huggingface.co/zai-org/GLM-5. Paper: htt...
How to create your own custom conversation app on Reachy Mini 🤖💬
Get a Reachy Mini : https://pollen-robotics-reachy-mini.hf.space The Apps : https://pollen-robotics-reachy-mini.hf.space/#/apps Reachy Mini Astronomer : https://huggingface.co/spaces/dlouapre/reach...
Kimi K2.5 vs Claude Code (REAL Use Cases): New KING of Coding??
Kimi K2.5 vs Claude Code on REAL software engineering tasks! Testing open source vs proprietary AI coding agents on 3 practical challenges developers face daily. Tasks tested: 1. Frontend: Convert...
MoE Token Routing Explained: How Mixture of Experts Works (with Code)
This video dives deep into Token Routing, the core algorithm of Mixture of Experts (MoE) models. Slides: https://huggingface.co/ariG23498/moe-routing-algorithm/blob/main/MoE_routing_algorithm.pdf ...
Training Dashboards with Trackio + Hugging Face
Integrate Trackio directly with Hugging Face Hub and automatically log, push, and visualize your training metrics on the model page. --- 🔗 *Links* - 📈 Trackio Blog Post: https://huggingface.co/bl...
OpenAI Agents SDK Crash Course (with Hugging Face Models)
Build production-ready LLM agents with the OpenAI Agents SDK. --- 🔗 Links - Agents Series Playlist: https://www.youtube.com/playlist?list=PLo2EIpI_JMQsw73Q7febEuUFBFcqIg2Mq - Code from the video: ...
Reachy Mini at Nvidia's Jensen CES keynote
Building Agents with Smolagents
Learn how to create minimalist agents with open models using Smolagents by Hugging Face. --- 🔗 *Links* - 🧑💻 Code from the video: https://github.com/huggingface/hub-tutorials/blob/main/notebooks/0...
How to contribute to Open Source - 7 EASY steps 🤗
This video walks through the steps of making an open-source contribution, with a practical example of fixing a bug in Trackio with Cursor.
HuggingChat | Chat with Open Models
--- ⏰ *Timestamps* 0:00:00 - Intro 0:00:09 - Overview of Hugging Chat 0:00:54 - Using OmniRouter 0:02:14 - Exploring the HF MCP server 0:03:50 - Dynamic Spaces 0:04:26 - Searching models ...
Steering LLM Behavior Without Fine-Tuning
Modify the behavior or the personality of a model at inference time, without fine-tuning or prompt engineering. Read the blog post 👉 https://huggingface.co/spaces/dlouapre/eiffel-tower-llama Explo...
Claude Code can generate AI images for your apps/websites with 🤗 Hugging Face
How to use Hugging Face models on VS Code Copilot
Links --- Install the VS Code extension: https://marketplace.visualstudio.com/items?itemName=HuggingFace.huggingface-vscode-chat Check out Inference Providers here: https://huggingface.co/docs/infe...
How to use Hugging Face 🤗 models on VS Code
LeRobot Worldwide Hackathon
We are LIVE! LeRobot Wolrdwild Hackathon is turning the world into one giant AI robotics lab! We’re living in wild times. The “ChatGPT moment” for robotics might be just around the corner. Help sha...
Inference Providers: Best Way to Build with Open Source Models
Create your account Today 👉 https://huggingface.short.gy/join Learn how to call open-source AI models through one consistent Hugging Face Inference Providers API: run chat completions with LLMs, g...
Gradio 6 Launch 🏎️🏁
Gradio 6 is finally here! And it's lighter, faster, and more customizable than ever! Our core team will walk you through the latest features and answer your questions. You wont want to miss this!...
The Power of Open Source: Building Giants in the Open
Explore how open-source AI powers production today: candid lessons from European founders (n8n, Black Forest Labs), a pragmatic tour of the open infra stack (Snowflake, OpenAI, NVIDIA, Supabase/Pos...
MCP's 1st Birthday Kickoff
🎉 MCP’s 1st Birthday Hackathon — Kickoff Livestream Welcome to the official kickoff for MCP’s 1st Birthday Hackathon, hosted by Anthropic + Gradio. We’ll also be joined by folks from Anthropic, Op...
MCP's 1st Birthday Kickoff 📱
🎉 MCP’s 1st Birthday Hackathon — Kickoff Livestream Welcome to the official kickoff for MCP’s 1st Birthday Hackathon, hosted by Anthropic + Gradio. We’ll also be joined by folks from Anthropic, Op...
Making an open-source contribution, in 7 easy steps
This video walks through the steps of making an open-source contribution, with a practical example of fixing a bug in Trackio with Cursor: https://huggingface.co/docs/trackio/en/index
Reachy Mini recognizes itself in the mirror
Remi plugged GPT-4o on Reachy Mini and it's pretty cool! Some new capabilities: - Image analysis: Reachy Mini can now look at a photo it just took and describe or reason about it - Face tracking: k...
Trackio: A DROP-IN Replacement for W&B that is open-source and 💯 free
This video provides an overview and demo of Trackio, which is a free, experiment tracking library Hugging Face just released. Install Trackio: pip install trackio Documentation: https://huggingfa...