热点
"跨模态注意力" 相关文章
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
cs.AI updates on arXiv.org 2025-08-01T04:08:31.000000Z
PatchTraj: Dynamic Patch Representation Learning for Time-Frequency Trajectory Prediction
cs.AI updates on arXiv.org 2025-07-28T04:42:54.000000Z
Gated Recursive Fusion: A Stateful Approach to Scalable Multimodal Transformers
cs.AI updates on arXiv.org 2025-07-08T05:53:54.000000Z