Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs

Documenti analoghi

• Large Language Models are Strong Audio-Visual Speech Recognition Learners
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2024)
• MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2025)
• Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
  di: Cappellazzo, Umberto, et al.
  Pubblicazione: (2025)
• Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
  di: Yeo, Jeong Hun, et al.
  Pubblicazione: (2025)
• Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs
  di: Anand, et al.
  Pubblicazione: (2025)