PPL
Zhipeng Zhang
Papers (5)
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use AgentsA Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLMSilent Collapse in Recursive Learning SystemsTowards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action ModelsStellar Age Compression Reshapes Interpretations of the Milky Way Thick-Disk Formation History