SyncRA: Learning Temporal Correspondence in Omni-Modal Models
The proposed Synchrony-Guided Representation Alignment (SyncRA), a lightweight method for strengthening temporal correspondence between audio and vision, consistently outperforms answer-only fine-tuning across all model-benchmark combinations, while substantially improving the ability to track changing audio-visual pai...
Ze-Long Xu, Yan Li, Wen-He Hu et al.
· 0 citations