Jia-Bin Huang

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...

This is GOAT! I now use the BUT/THEREFORE template for all my video scripts.

thanks for coming to my TED Talk

Here's a simple fix:

Instead of just presenting information, tell a story.

A story about how you encounter a problem, solve it, introduce a new conflict, and resolve it, and so on.

Keep creating curiosity loops to engage/re-hook your audience.

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!

YouTube video by Jia-Bin Huang This Simple Optimizer Is Revolutionizing How We Train AI [Muon]

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

YouTube video by Jia-Bin Huang How AI Taught Itself to See [DINOv3]

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

YouTube video by Jia-Bin Huang The Weirdly Small AI That Cracks Reasoning Puzzles [HRM]

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

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...

*Slides without slide titles*

When I first tried presenting WITHOUT slide titles, everything flowed so much better! (totally validated ... by me)!

Give it a shot! Once you try it, you’ll never want to go back.

*Empty initial slides*

What’s a better starting point than that default slide layout?

A completely blank slide.

It helps you explore the design space and focus on delivering a clear, compelling story.

*Bullet points*

The second thing the layout prompts you to do?
("Click to add text").

Start a bullet list.

Among so many creative forms of presenting your ideas, it nudges you toward the most boring one: a list. 🔢

*Slide title*

The first thing this layout does is to ask you to add a slide title.

Seems reasonable, right? visuals, this encourages you to
1) lead your presentation with text instead of visuals and
2) cram in many titles in a talk, making it harder to maintain a narrative flow.

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? 🤔

Thanks! Yup, I hope to cover some fun computer vision applications. Stay tuned!

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?...

YouTube video by Jia-Bin Huang Policy Gradient in One Minute

No time? I’ve got your back!

Check out Policy Gradient in One Minute!
youtu.be/p9k9YUdnNlk

Have fun!

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?

YouTube video by Jia-Bin Huang One Step, Big Leap: The Simple Idea Transforming Generative AI

Check out the video to learn this new, elegant formulation of generative models!

youtu.be/swKdn-qT47Q

Awesome! 🤩

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

We had a blast at CVPR2025!

There was so much to learn! I am particularly excited to meet many new friends and reconnect with old ones.

I feel energized. Already looking forward to the next one!

Thanks a lot!

Kullback–Leibler (KL) divergence is a cornerstone of machine learning.

We use it everywhere, from training classifiers and distilling knowledge from models, to learning generative models and aligning LLMs.

BUT, what does it mean, and how do we (actually) compute it?

Video: youtu.be/tXE23653JrU

My X/Twitter account has been hacked... Please don't believe what they said!

Trying to get it back in the meantime. Sorry for the inconvenience!

How LLMs Learn to Reason with Reinforcement Learning

Full video: www.youtube.com/watch?v=mg-i...