作者位次 #3/6ICML 2026Poster· Applications / Computer Vision
AnyCanvas: Potential Field Guidance for Training-Free Spatial Control in Text-to-Image Diffusion
Tianyi Xie · Zhiyuan Yu · kaihong huang · Beilun Wang · Zhaoyang Wang · Dian Shen
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。
Tianyi Xie · Zhiyuan Yu · kaihong huang · Beilun Wang · Zhaoyang Wang · Dian Shen
Runhuai Chen · Dian Shen · Dandan Zhang · kaihong huang · Linghui Meng · Beilun Wang
Text-attributed graphs (TAGs) require jointly modeling relational structure and node-level text. Existing GNN-LLM approaches perform by incorporating large language models at inference time for processing the text attributes, resulting in costly deployment. More fundamentally, LLM knowledge is ty...