SFT induces pseudo-reasoning paths that undermine RL in LVLMs, while RL with GRPO and mixed perception-cognition rewards on the new VLAA-Thinking dataset produces more genuine reasoning and top leaderboard performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
SFT induces pseudo-reasoning paths that undermine RL in LVLMs, while RL with GRPO and mixed perception-cognition rewards on the new VLAA-Thinking dataset produces more genuine reasoning and top leaderboard performance.