一作NeurIPS 2026PosterOne Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-TuningXinrui Chen · Liu Yang · Ou Wu强化学习与后训练数据与预训练OpenReview
作者位次 #2/5NeurIPS 2026PosterDRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularizationqing liu · Xinrui Chen · Weiyao Zhu · Yi Du · Ou Wu强化学习与后训练OpenReview