一作NeurIPS 2026Poster
Quantifying and Optimizing Path Uncertainty in Masked Diffusion Models
Ziyu Chen · Xinbei Jiang · PENG SUN · Tao Lin
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ziyu Chen · Xinbei Jiang · PENG SUN · Tao Lin
Ziyu Chen · Yilun Zhao · Chengye Wang · Rilyn R. Han · Manasi Patwardhan · Arman Cohan
Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and realism. To address this challenge, we introduce the synthesize-and-reground framework, a two-stage pipeline comprising: (1) Claim-Centric QA...