conftrace_

reward reasoning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multi-stage reinforcement learning (1) reinforcement learning with verifiable reward (1) multimodal reward model (1) cross-modal knowledge distillation (1) visual understanding (1) foundation model (1) reward model (1) generative model (1) preference learning (1)

Papers

GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning AAAI 2026 MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning CVPR 2026