Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions.

Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these capabilities using task feedback, but current on-policy RL runtimes execute rollout, reference…