Dynamic Important Example Mining for Reinforcement Finetuning
DIEM is proposed, a principled and fully automated framework that makes data utilization adaptive throughout RFT and consistently outperforms strong static and dynamic baselines.
We have 2 of 4 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
DIEM is proposed, a principled and fully automated framework that makes data utilization adaptive throughout RFT and consistently outperforms strong static and dynamic baselines.
HDR-RoPE is proposed, which extends RoPE from independent 2D rotations to higher-dimensional rotations and introduces a Paley-I orthogonal basis to obtain balanced, isotropic, and dense phase mixing within each rotation subspace and significantly enhances channel coupling and rotational degrees of freedom while maintai...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.