This work reformulate homogeneous distance minimization as a bi-level optimization problem via a matching-and-approximating paradigm and introduces a difficulty-aware marginal reweighting mechanism to emphasize informative instances while preserving global geometric consistency.
Xiao Cui, Yu-Lei Qin, Mo Zhu et al.· IEEE Transactions on Pattern...· 1 citation
Groupwise Reward Geometry Conditioning (GRGC) is proposed, a two-stage framework that improves advantage construction by shaping student-side reward groups during both critic training and policy optimization, and introduces negligible overhead over GAD.
The Multi-Level Optimal Transport (MultiLevelOT) is introduced, a novel approach that advances the optimal transport for universal cross-tokenizer knowledge distillation and is robust to different student and teacher models across model families, architectures, and parameter sizes.
Xiao Cui, Mo Zhu, Yu-Lei Qin et al.· IEEE Transactions on Pattern...· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.