#artificial intelligence
Sep 2026
Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception
This work augments the LALM with a dedicated frame-level grounding model while leveraging its semantic modeling capability to represent the event query, and shows that the grounding model can provide temporal evidence to support downstream reasoning.
Yan Shi, Yan Song, Jun-Hui Li et al.
· arXiv.org · 0 citations