论文解读
PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding
长音频理解 | 7.4/10
检索增强生成
论文解读
Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow
音频生成 | 8.0/10
论文解读
Interval-Aware Retrieval Framework For Speech-Based Automatic Alzheimer’s Detection
语音生物标志物 | 8.5/10
论文解读
SceneRAG: Scene-Level Retrieval-Augmented Generation for Video Understanding
视频理解 | 7.5/10