Speculative Decoding is the coolest trick for speeding up LLM inference! Check out the video and learn why rejection sampling preserves quality, and how methods such as draft trees, Medusa, MTP, EAGLE, and DFlash further accelerate LLM inference. youtu.be/l8gWQlrVOKQ

Two API Calls Exposed AI's Hidden Reasoning Such a cool attack exploits a vulnerability in frontier models. Just replay encrypted reasoning traces through weaker models and recover the hidden reasoning! 🤯 Many fun reasoning examples! New video: youtu.be/P1v1-2CCKD0

Two API Calls Exposed AI's Hidden Reasoning

YouTube video by Jia-Bin Huang

youtu.be

How Small Models Learn to Think Like Giants On-policy distillation has emerged as a powerful way to transfer knowledge between models. BUT, how do they work? 🤔 In this video, let's explore knowledge distillation from first principles. youtu.be/YH0YXgDWZXA

How Small Models Learn to Think Like Giants

YouTube video by Jia-Bin Huang

youtu.be

LoRA, low-rank adaptation, is arguably the most popular parameter-efficient fine-tuning method for LLMs. But how does it actually work? Check out the video to learn LoRA and friends (LoRA+, QLoRA, VeRA, and DoRA)! youtu.be/U80tjcThl9Q

I didn't know what JEPA is, and at this point I am too afraid to ask ...😬 so I made a video tracing the last 30+ years of self-supervised learning, covering ideas from contrastive learning, distillation, masked modeling, JEPA, and world models. youtu.be/gVEr2cnDE_8

The 60-Year Hunt for AI's Most Important Function I was trying to understand how SwiGLU works, but I couldn’t find an explanation that clicked for me. So I made this video to explain it from first principles. Check it out: youtu.be/JRaPNrpsQ9s

**Modern Transformer - Complete Guide** Interested in learning the recent advances in transformers? After 14 videos, I've finally completed this series! 🥳🥳🥳 Check out the course here: www.youtube.com/playlist?lis...

The Most Underrated Layer Inside Every AI Model Virtually every AI model has normalization layers. BUT, what makes them so essential? 🤔 New video on learning the role of normalization in stabilizing training and alternatives like DyT and Derf. youtu.be/JHl_gwVoh-k

How is DeepSeek V4 so INSANELY cheap? 🤔 Compared to a GQA baseline, it's new *compressed attention* mechanism (CSA and HCA) slashes the KV cache memory cost by 98% 🤯 at a 1M-token context! Here’s how: youtu.be/q8holiIirgo

How do we make attention actually capture context? Exclusive Self Attention (XSA) is an interesting variant that improves attention with minimal cost in speed & memory. Check out the video here: youtu.be/2eZKT4H9_iQ

**Modern Transformer architecture explained** I compiled a list of videos on the Transformer architecture into a short "YouTube course". www.youtube.com/playlist?lis... Hopefully, this would be helpful for beginners in the community. Happy learning! 😎

Finally got some time to read the DeepSeek Engram paper! Idea: Replace repeated reconstruction with direct lookup of common knowledge. It’s so intuitive that it feels strange this wasn’t part of the design from the start. Video summary here: youtu.be/87Q8nf1XHKA

New video! How do LLMs grow outrageously large yet blazingly fast? The secret: Mixture of Experts (MoE) In this video, we cover the role of FFNs, how to scale them without slowing down, and how to maintain load balance and training stability. Full video here: youtu.be/0QQlYR1r6pQ

How LLMs Get Outrageously Large Yet Blazingly Fast [MoE]

YouTube video by Jia-Bin Huang

youtu.be

Beyond softmax attention Linear attention and its variants enable faster inference without growing the KV cache. Let’s learn the core ideas behind efficient sequence modeling. youtu.be/pUCWwGR5WmQ

Beyond Softmax: The Future of Attention Mechanisms

YouTube video by Jia-Bin Huang

youtu.be

Residual connections are adopted in virtually every deep learning model. BUT, can we further improve it? Hyper-connections is an exciting recent exploration to generalize residual connections. Check out the video explaining manifold constraints hyper-connections! youtu.be/jYn_1PpRzxI

How Residual Connections Are Getting an Upgrade [mHC]

YouTube video by Jia-Bin Huang

youtu.be

Introducing *Edit-by-Track*, a framework that enables precise video motion editing via 3D point tracks. Our method supports a wide range of motion editing applications, including object removal, shape deformation, dynamic view synthesis, and many more! Video explainer: youtu.be/aAj6PIgx20o

Wondering how DeepSeek v3.2 rivals SOTA models (e.g., GPT5/Gemini 3 pro) while being ~30x cheaper? 🤔 Let's learn how the base model works! We'll focus on attention, the need for KV caching, and key ideas for improving attention (MQA/GQA/MLA/DSA). youtu.be/Y-o545eYjXM

Sharing the slides for a talk on faculty job search Hope it's helpful to people exploring and preparing for the process. Feedback is welcome! www.dropbox.com/scl/fi/p7xdt...

How to organize your talk? I used to present like this, thinking that I was being "academic", "organized", and "professional". BUT, from the audience's viewpoints, this sucks. 😱 Look how far they need to hold a long-term context to just make sense of what you're saying!

Muon is a (relatively) new optimizer that powered large-scale training of recent foundation models, e.g., Kimi K2 and GLM 4.5. Interested in learning how it works? Check out the video here: youtu.be/bO5nvE289ec

This Simple Optimizer Is Revolutionizing How We Train AI [Muon]

YouTube video by Jia-Bin Huang

youtu.be

How AI Taught Itself to See Self-supervised learning is fascinating! How can AI learn from images only without labels? In this video, we’ll build the method from first principles and uncover the key ideas behind CLIP, MAE, SimCLR, and DINO (v1–v3). Video link: youtu.be/oGTasd3cliM

How AI Taught Itself to See [DINOv3]

YouTube video by Jia-Bin Huang

youtu.be

New video! A quick dive into the recent Hierarchical Reasoning Model (HRM) through the lens of algorithm synthesis. Check it out: youtu.be/RK7lysjz_G0

The Weirdly Small AI That Cracks Reasoning Puzzles [HRM]

YouTube video by Jia-Bin Huang

youtu.be

Diffusion LLMs are promising ways to overcome the limitations of autoregressive LLMs. Less error propagation, easier to control, and faster to sample! But how do Diffusion LLMs actually work? 🤔 In this video, let's explore some ideas on this fascinating topic! youtu.be/8BTOoc0yDVA

In an era of billion-parameter models everywhere, it's incredibly refreshing to see how a fundamental question can be formulated and solved with simple, beautiful math. - How should we orient a solar panel ☀️🔋? - Zero AI! If you enjoy math, you'll love this! Video: www.youtube.com/watch?v=ZKzL...

Why is the "Title and Content" slide layout BAD? Most people prepare their presentation from this default layout. I used it for years without questioning it. BUT, this essentially guides you toward developing poor presentation. Why? 🤔

Kids’ summer camp just kicked off, and that means... I finally have time to make new videos! What topics are you most interested in right now?

Why More Researchers Should be Content Creators Just trying something new! I recorded one of my recent talks, sharing what I learned from starting as a small content creator. youtu.be/0W_7tJtGcMI We all benefit when there are more content creators!

Fresh out of the oven! 🍞 @jbhuang0604.bsky.social breaks down Mean Flow from Kaiming’s group in his latest video. Video: youtu.be/swKdn-qT47Q?...

Policy gradient methods rock! These are the core techniques for making your transformer "chat" and "reason", a robot that manipulates objects, and a drone that maneuvers in a complex environment. BUT, how do we learn all the developments in the past 30+ years?

Awesome! 🤩 So glad to hear the authors enjoyed the video, totally made my day!