Research

Foundation-model training, numerical reliability, and reliable agents.

Current research

Harbin Institute of Technology (HIT) · Research with Prof. Dimitrios Stamoulis · 2025 – Present

  • Numerical reliability of robotics foundation models

    Identified batch-dependent inference drift across 10+ robotics models and demonstrated changes in task outcomes. Developing reusable operators for numerically consistent robot inference.

  • DreamZero: high-throughput WAM rollout engine

    Designing a distributed, asynchronous rollout system for world-action-model RL, focusing on high-throughput sampling, actor/learner execution, and numerical parity between rollouts and training.

  • Low- and mixed-precision adaptation of VLAs and WAMs

    Investigating FP8/FP4 full-model and LoRA fine-tuning, measuring training efficiency, optimization stability, and downstream policy behavior.

Publications

More on Google Scholar