Jia-Bin Huang

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...

Ha! Yes, Seungjae insisted that we call this IVE.

RL is so back!

Reinforcement learning is a key driver in aligning LLMs and enhancing their reasoning capabilities.

BUT, it’s a tricky topic to wrap your head around (at least for myself 😵‍💫).

So, I put up a video breaking down the basics in a way that clicked for me. I hope it helps you, too!

I find TRPO's idea of learning from others' experiences fascinating.

So, I started running TRPO for my group, making all (previously individual) feedback on experiments, writing, rebuttals, and presentations public.

Now everyone gets to learn from each other’s trajectories!

Indeed!!

🥺

Brought to you by our amazing students Seungjae Lee, Daniel Ekpo, Haowen Liu, and faculty Furong Huang and Abhinav Shrivastava

Learn more at ive-robot.github.io

IVE leverages VLMs to
• extract semantic scene graphs,
• imagine novel scenes,
• predict their physical plausibility, and
• generate executable sequences.

IVE is a memory-guided agentic exploration framework that operates fully automatically, enabling more diverse and meaningful exploration.

Exploration is key for robots to generalize, especially in open-ended environments with vague goals and sparse rewards.

BUT, how do we go beyond random poking? Wouldn't it be great to have a robot that explores an environment just like a kid?

Introducing Imagine, Verify, Execute (IVE)!

Yup, it’s so much fun!

Solving high-impact real-world problems with multimodal foundation models

You are constantly leveling up your presentation!!