Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
I-Hung Hsu Profile picture
I-Hung Hsu
@IHung_Hsu
Research Scientist @Google; CS PhD from @USC in NLP; Work on making machines to be reliable, intelligent , and user-friendly tools for all.
Oct 31 • 6 tweets • 3 min read
🧠🚀 Excited to introduce Supervised Reinforcement Learning—a framework that leverages expert trajectories to teach small LMs how to reason through hard problems without losing their minds. 🤯

Better than SFT && RLVR.

Read more:

#llms #RL #reasoning huggingface.co/papers/2510.25…Image The struggle is real for small LMs on hard reasoning. 😣

📉 Too weak for RLVR: Can't find correct answers to reinforce.
🤯 Too small for SFT Distillation: Giant model strategies are alien concepts (way too off-policy) for them to grasp.

They need a bridge, not just more data. Image