When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA

Documenti analoghi

• Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
  di: Sriratanawilai, Sukrit, et al.
  Pubblicazione: (2025)
• Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
  di: Payoungkhamdee, Patomporn, et al.
  Pubblicazione: (2025)
• Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai
  di: Pengpun, Parinthapat, et al.
  Pubblicazione: (2024)
• WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai
  di: Limkonchotiwat, Peerat, et al.
  Pubblicazione: (2025)
• Space Decomposition for Sentence Embedding
  di: Ponwitayarat, Wuttikorn, et al.
  Pubblicazione: (2024)