This work identifies a robust failure mode that is accompanied by a widening gap between in-loop metric gains and gains measured on independent held-out evaluations and proposes Diversity-Aware Proposal Sampling (DAPS), a lightweight mitigation that combines category-coverage reweighting, persistent edit memory, and a...
CostAda is introduced, a cost-calibrated adaptive controller built around a cost-calibrated frontier utility that reaches the strongest baseline's full-budget quality with at most half the budget on twelve of sixteen benchmark--backbone pairs while achieving the strongest mean final quality on all eight benchmarks unde...
Yansen Zhang, Yilu Liu, Tianyu Liu et al.· arXiv.org· 0 citations
AdaMTP is proposed, an adaptive training paradigm that dynamically aligns the prediction horizon with the intrinsic predictability of the sequence, and consistently outperforms standard MTP in both task performance and inference speedup.
Ziqiang Cui, Han Shi, Bowei He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.