LHRMs (Large Hybrid-Reasoning Models) code & checkpoints referenced in paper 2505.14631 not found

Hi UniLM team,

The recent paper “Think Only When You Need with Large Hybrid-Reasoning Models” states that its code and models would be released in this repository.

I’ve searched the repo (branches, tags, sub-modules) as well as open/closed issues and PRs, but couldn’t locate any files related to LHRMs models or checkpoints, Hybrid Fine-Tuning (HFT) scripts or Hybrid Group Policy Optimization (HGPO) RL pipeline.

Could you please clarify whether the LHRMs are resources already available under a different path or branch that I might have missed? Or if they are still being prepared, is there an estimated timeline for release?

Many thanks for making so many research projects publicly available—looking forward to experimenting with LHRMs as well!