Introduces TA-MDP and proves GRPO convergence at O(1/sqrt(T)), a reward decomposition bound, and PAC-Bayes generalization for tool-augmented LVLM policies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization
Introduces TA-MDP and proves GRPO convergence at O(1/sqrt(T)), a reward decomposition bound, and PAC-Bayes generalization for tool-augmented LVLM policies.