Mengdi Wang is a PhD candidate in computer science researching scalable, GPU-accelerated systems for multiscale physical simulation.
Based on 3 scored articles
Referenced in coverage
“Co-authored research on AI agent skills showing retrieval as separate bottleneck with precision falling from 29.6% to 3.3% as pools grow.”
“Co-author contributing to MemEye evaluation of multimodal agent long-term memory systems.”
“Co-author of the OpenClaw-RL framework research on asynchronous agent training with hindsight-guided distillation.”