Jia-Bin Huang
@jbhuang0604.bsky.social
Associate Professor at UMD CS. YouTube: https://youtube.com/@jbhuang0604
Interested in how computers can learn and see.
Interested in how computers can learn and see.
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...
Hope it's helpful to people exploring and preparing for the process.
Feedback is welcome!
www.dropbox.com/scl/fi/p7xdt...
November 21, 2025 at 4:42 AM
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...
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!
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!
October 29, 2025 at 7:27 PM
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!
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
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
October 24, 2025 at 9:03 PM
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
Interested in learning how it works?
Check out the video here: youtu.be/bO5nvE289ec
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
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
September 16, 2025 at 11:13 PM
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
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
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
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
August 15, 2025 at 9:38 PM
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
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
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
August 8, 2025 at 2:44 AM
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
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...
- How should we orient a solar panel ☀️🔋? -
Zero AI! If you enjoy math, you'll love this!
Video: www.youtube.com/watch?v=ZKzL...
July 16, 2025 at 2:25 PM
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...
- 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? 🤔
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? 🤔
July 8, 2025 at 11:26 AM
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? 🤔
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?
I finally have time to make new videos!
What topics are you most interested in right now?
July 1, 2025 at 9:51 AM
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?
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!
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!
June 24, 2025 at 9:58 PM
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!
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!
Reposted by Jia-Bin Huang
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?...
Video: youtu.be/swKdn-qT47Q?...
June 19, 2025 at 10:24 PM
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?...
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?
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?
June 20, 2025 at 11:08 PM
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?
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!
So glad to hear the authors enjoyed the video, totally made my day!
June 20, 2025 at 4:09 PM
Awesome! 🤩
So glad to hear the authors enjoyed the video, totally made my day!
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!
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!
June 17, 2025 at 2:38 PM
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!
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!
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
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
June 4, 2025 at 2:58 PM
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
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!
Trying to get it back in the meantime. Sorry for the inconvenience!
June 3, 2025 at 6:11 PM
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!
Trying to get it back in the meantime. Sorry for the inconvenience!
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!
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!
May 21, 2025 at 5:14 PM
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!
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!
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!
May 19, 2025 at 2:29 PM
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!
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!
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)!
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)!
May 14, 2025 at 1:33 PM
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)!
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)!
Solving high-impact real-world problems with multimodal foundation models
April 26, 2025 at 4:57 PM
Solving high-impact real-world problems with multimodal foundation models
Check out UrbanIR - Inverse rendering of unbounded scenes from a single video!
It’s a super cool project led by the amazing Chih-Hao!
@chih-hao.bsky.social is a rising star in 3DV! Follow him!
Learn more here👇
It’s a super cool project led by the amazing Chih-Hao!
@chih-hao.bsky.social is a rising star in 3DV! Follow him!
Learn more here👇
✨What if we could transform a daytime driving video into a realistic nighttime scene—without ever stepping outside again?
We introduce UrbanIR, a neural rendering framework for 💡relighting, 🌃nighttime simulation, and 🚘 object insertion—all from a single video of urban scenes!
We introduce UrbanIR, a neural rendering framework for 💡relighting, 🌃nighttime simulation, and 🚘 object insertion—all from a single video of urban scenes!
March 15, 2025 at 1:49 PM
Check out UrbanIR - Inverse rendering of unbounded scenes from a single video!
It’s a super cool project led by the amazing Chih-Hao!
@chih-hao.bsky.social is a rising star in 3DV! Follow him!
Learn more here👇
It’s a super cool project led by the amazing Chih-Hao!
@chih-hao.bsky.social is a rising star in 3DV! Follow him!
Learn more here👇
Interesting! I didn't realize how important a video title/packaging is until now.
It's the same video, but with a better packaging it gets much more attention.
It's the same video, but with a better packaging it gets much more attention.
March 10, 2025 at 9:34 PM
Interesting! I didn't realize how important a video title/packaging is until now.
It's the same video, but with a better packaging it gets much more attention.
It's the same video, but with a better packaging it gets much more attention.
How a 40-Year-Old Trick Solves Seamless Image Blending
Laplacian pyramid blending is a simple yet effective tool for many applications, including object composition, seamless panorama stitching, and exposure fusion.
Let’s learn this classic method that still works so well today.
Laplacian pyramid blending is a simple yet effective tool for many applications, including object composition, seamless panorama stitching, and exposure fusion.
Let’s learn this classic method that still works so well today.
March 9, 2025 at 3:27 PM
How a 40-Year-Old Trick Solves Seamless Image Blending
Laplacian pyramid blending is a simple yet effective tool for many applications, including object composition, seamless panorama stitching, and exposure fusion.
Let’s learn this classic method that still works so well today.
Laplacian pyramid blending is a simple yet effective tool for many applications, including object composition, seamless panorama stitching, and exposure fusion.
Let’s learn this classic method that still works so well today.
Fifth year grad students to incoming ones at the prospective student visit day:
March 4, 2025 at 3:20 AM
Fifth year grad students to incoming ones at the prospective student visit day: