Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting

Documenti analoghi

• MiLorE-SSL: Scaling Multilingual Capabilities in Self-Supervised Models without Forgetting
  di: Xu, Jing, et al.
  Pubblicazione: (2026)
• Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models
  di: Xu, Jing, et al.
  Pubblicazione: (2024)
• DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
  di: Chen, Xueyuan, et al.
  Pubblicazione: (2025)
• SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR
  di: Zhao, Qiuming, et al.
  Pubblicazione: (2024)
• Efficient Multilingual ASR Finetuning via LoRA Language Experts
  di: Li, Jiahong, et al.
  Pubblicazione: (2025)