智能AI None FAIR-Calib:用于扩散大语言模型训练后量化的前沿感知不稳定性重新加权校准 2026-06-08 Haoyu Huang, Linlin Yang, Sheng Xu, Boyu Liu, Guodong Guo, Zhongqian Fu, Hang Zhou, Baochang Zhang
智能AI None Elmes*:长尾教育场景中大型语言模型细粒度评估标准的自动构建 2026-06-08 Tao Liu, Ye Lu, Ruohua Zhang, Siyu Song, Wentao Liu, Aimin Zhou, Hao Hao
智能AI None 立场:不要只是“事后修复”:人工智能科学必须研究训练动态 2026-06-08 Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah, Catherine Arnett, Fazl Barez, Naomi Saphra
智能AI None 代理人工智能控制评估中的攻击选择会显着降低安全性 2026-06-08 Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad IV, Joachim Schaeffer, Ram Potham, Tyler Tracy
智能AI None CrowdMath:众包数学研究讨论的数据集 2026-06-08 Sherin Muckatira, Jesse Geneson, Slava Gerovitch, Pavel Etingof, Mikhail Gronas, Anna Rumshisky
智能AI None Lean4Agent:代理工作流程和轨迹的形式化建模和验证 2026-06-08 Ruida Wang, Jerry Huang, Pengcheng Wang, Xuanqing Liu, Luyang Kong, Tong Zhang
智能AI None SafeGene:可重复使用的适配器,用于可转移的安全对准 2026-06-08 Yanghan Wang, Zhiqiang Kou, Fu Feng, Jing Wang, Xin Geng
智能AI None DiBS:扩散通知分支选择 2026-06-08 Bo Liu, Yuan Xie, Yuan Gao, Xiaolong Luo, Peng Ye, Tao Chen, Fujun Han