RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Documenti analoghi

• ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
  di: Feng, Sicheng, et al.
  Pubblicazione: (2025)
• SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
  di: Tuo, Kaiwen, et al.
  Pubblicazione: (2025)
• MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
  di: Wang, Chenglong, et al.
  Pubblicazione: (2026)
• Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
  di: Chen, Honghao, et al.
  Pubblicazione: (2025)
• ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
  di: Abboud, Elie, et al.
  Pubblicazione: (2026)