Users expressed excitement about the ELASTIC paper on using RL to optimize scaling and test-time compute in diffusion robot policies, praising the work as interesting and celebrating it as a first MS publication.
Based on 2 visible X reactions from 2 accounts; directional sample.
Ask a question below.
Published answers will appear here.
Before we start, just wanted to say I'm very excited to share the first paper of my MS! Huge thanks to @g_k_swamy, @ybisk, and my advisor @andrea_bajcsy! Paper: https://arxiv.org/abs/2606.31132
@andrewzouli Interesting work Andrew! When it comes to the rewards you used, are the parameters transferable if we aim to benchmark the method across various models?
Before we start, just wanted to say I'm very excited to share the first paper of my MS! Huge thanks to @g_k_swamy, @ybisk, and my advisor @andrea_bajcsy! Paper: https://arxiv.org/abs/2606.31132
@andrewzouli Interesting work Andrew! When it comes to the rewards you used, are the parameters transferable if we aim to benchmark the method across various models?
Users expressed excitement about the ELASTIC paper on using RL to optimize scaling and test-time compute in diffusion robot policies, praising the work as interesting and celebrating it as a first MS publication.
Based on 2 visible X reactions from 2 accounts; directional sample.
Ask a question below.
Published answers will appear here.