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
Who's Who of AI
Jia-Bin Huang
Why they matter
Researcher with public evidence across AI research, Compute & infrastructure.
- AI signals
- 2 past 30d
- Sources
- 1 distinct domains
- Discussions
- 0 past 30d
- Latest signal
- 5d ago
Associate Professor at UMD CS. YouTube: https://youtube.com/@jbhuang0604
Interested in how computers can learn and see.
What they're sharing
- YouTube youtube.com
How LLMs Get Faster Without Changing Their Outputs | Speculative Decoding youtu.be
Two API Calls Exposed AI's Hidden Reasoning youtu.be
Articles & links
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
Their network
In Jia-Bin Huang's orbit
Center = Jia-Bin Huang. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Jia-Bin Huang? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/jbhuang0604-bsky-social)