Mingze Li is a graduate research assistant at Georgia Tech Physical Internet Center and associated with the Department of Sociology at University of Washington.
How media typically covers Mingze Li
Mingze Li as author
Minimizing training-inference discrepancy and policy staleness enables reliable token-level surrogate optimization in RL with LLMs, with importance sampling correction and routing replay being essential for stable training at scale.
“Author of "Qwen Explains Why Minimizing Training-Inference Gaps and Policy Staleness Improv" on arXiv”