Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought

Documenti analoghi

• POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
  di: Li, Xuanchen, et al.
  Pubblicazione: (2025)
• MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates
  di: Huang, Zikang, et al.
  Pubblicazione: (2026)
• Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models
  di: Wang, Junyu, et al.
  Pubblicazione: (2025)
• ASDA: Audio Spectrogram Differential Attention Mechanism for Self-Supervised Representation Learning
  di: Wang, Junyu, et al.
  Pubblicazione: (2025)
• Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module
  di: Cui, Zhongjian, et al.
  Pubblicazione: (2025)