"au:"Kaiyuan Li"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Kaiyuan Li"" — arXiv2 Search

Showing 21–28 of 28 results

/ Date/ Name

Nov 20, 2025Progressive Supernet Training for Efficient Visual Autoregressive Modeling May 21, 2024FedASTA: Federated adaptive spatial-temporal attention for traffic flow prediction May 15, 2025ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts Jan 27, 2026CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation Mar 19, 2024Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai Jul 21, 2025EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent Apr 6, 2025The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models?Feb 20, 2025PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models