FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings

Documenti analoghi

• Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking
  di: Vendrame, Katia, et al.
  Pubblicazione: (2025)
• Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
  di: Sedláček, Šimon, et al.
  Pubblicazione: (2025)
• Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
  di: Hegde, Pradyoth, et al.
  Pubblicazione: (2025)
• ORCA: Open-ended Response Correctness Assessment for Audio Question Answering
  di: Sedláček, Šimon, et al.
  Pubblicazione: (2025)
• Robustness assessment of large audio language models in multiple-choice evaluation
  di: López, Fernando, et al.
  Pubblicazione: (2025)