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.
*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.
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.
July 8, 2025 at 11:26 AM
*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.
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.
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.
July 8, 2025 at 11:26 AM
*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.
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. 🔢
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. 🔢
July 8, 2025 at 11:26 AM
*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. 🔢
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.
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.
July 8, 2025 at 11:26 AM
*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.
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.
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!
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.
• 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.
May 14, 2025 at 1:33 PM
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.
• 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)!
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)!
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.