PPL
Yongjian Guo
Papers (5)
Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model RolloutsAdaptiveLoad: Towards Efficient Video Diffusion Transformer TrainingD-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action ModelsMissing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy CorrectionSword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training