Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Documenti analoghi

• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
  di: Wang, Weiyun, et al.
  Pubblicazione: (2025)
• MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity
  di: Liu, Yangzhou, et al.
  Pubblicazione: (2024)
• Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance
  di: Gao, Zhangwei, et al.
  Pubblicazione: (2024)
• VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
  di: Xu, Weiye, et al.
  Pubblicazione: (2025)
• Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
  di: Duan, Yuchen, et al.
  Pubblicazione: (2024)