Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models

Documenti analoghi

• Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
  di: Tan, Huajie, et al.
  Pubblicazione: (2025)
• Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
  di: Xue, Haotian, et al.
  Pubblicazione: (2025)
• From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
  di: Wang, Changpeng, et al.
  Pubblicazione: (2025)
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
  di: Wu, Junfei, et al.
  Pubblicazione: (2025)
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
  di: Lee, Daeun, et al.
  Pubblicazione: (2026)