一作ICML 2026Poster· Deep Learning / Generative Models and Autoencoders
DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
Qirui Jiao · Daoyuan Chen · Yilun Huang · Xika Lin · Ying Shen · Yaliang Li
多模态OpenReview
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。
Qirui Jiao · Daoyuan Chen · Yilun Huang · Xika Lin · Ying Shen · Yaliang Li
Ting Zhou · Daoyuan Chen · Qirui Jiao · Bolin Ding · Yaliang Li · Ying Shen
Qirui Jiao · Dian Jiao · Nan Du · Ying Shen · Liang Lin
Large Language Models (LLMs) have shown remarkable capabilities in Tool-Integrated Reasoning (TIR). However, the practical application is often hindered by frequent errors in tool invocations, such as incorrect parameters or malformed formats. Prevailing training paradigms, such as Supervised Fin...