作者位次 #3/6ACL 2026Findings· Findings of ACL
Bridging the Temporal Gap in Multimodal LLM s: Deeply Stacking Temporal Tokens for Audio-Visual Speech Recognition
Liyong Wang · Junliang Xing · Tianyu Hu · Jianfei Jiang · Jihuai Zhao · Huimin Ma
摘要
Audio-Visual Speech Recognition enhances speech recognition robustness in noisy conditions by leveraging visual cues. However, current Multimodal LLMs suffer from a fundamental temporal gap. This gap is characterized by limited fine-grained temporal modeling in vision encoders and progressive tem...