Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning

Documenti analoghi

• VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  di: Deng, Huilin, et al.
  Pubblicazione: (2024)
• WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
  di: Yang, Jie, et al.
  Pubblicazione: (2025)
• Bidirectional Progressive Transformer for Interaction Intention Anticipation
  di: Zhang, Zichen, et al.
  Pubblicazione: (2024)
• PEAR: Phrase-Based Hand-Object Interaction Anticipation
  di: Zhang, Zichen, et al.
  Pubblicazione: (2024)
• Intention-driven Ego-to-Exo Video Generation
  di: Luo, Hongchen, et al.
  Pubblicazione: (2024)