Skip to content
conftrace_

multi-stage reinforcement learning

1 paper

Explore in graph

Also known as

MSRL

Co-occurring keywords · papers mentioning both

reward reasoning (1) reinforcement learning with verifiable reward (1) multimodal reward model (1) cross-modal knowledge distillation (1) visual understanding (1)

Papers

MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning CVPR 2026