2 papers
cs.IR2026
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
Ruixiao Sun, Diego Uribe Mora, Zhimeng Jiang +7
Capturing user interests across extensive watch histories is critical for short-form video recommendation, yet scaling sequence length is limited by two bottlenecks: the semantic s…
cs.RO2026
PartDexTOG: Generating Dexterous Task-Oriented Grasping via Language-driven Part Analysis
Weishang Wu, Yifei Shi, Zhizhong Chen +1
Task-oriented grasping is a crucial yet challenging task in robotic manipulation. Despite the recent progress, few existing methods address task-oriented grasping with dexterous ha…