GRPO

SLCA-GRPO: Addressing Cross-Segment Credit Misassignment in Tool-Calling Reinforcement Learning

SLCA-GRPO separates tool and summary credit, improving success, cutting tool turns, and avoiding extra rollout…

AV-GRPO: Anchored-Modality Decoupled Diffusion Reinforcement Learning for Joint Audio-Video Generation

AV-GRPO is described as a GRPO-based reinforcement learning framework for joint audio-video models. It targets…