Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

Documenti analoghi

• Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift
  di: Xu, Qinwu
  Pubblicazione: (2026)
• SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
  di: Liu, Liangxin, et al.
  Pubblicazione: (2024)
• Low-Rank Quantization-Aware Training for LLMs
  di: Bondarenko, Yelysei, et al.
  Pubblicazione: (2024)
• Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
  di: Liu, Zijun, et al.
  Pubblicazione: (2024)
• GEM: A Gym for Agentic LLMs
  di: Liu, Zichen, et al.
  Pubblicazione: (2025)