AI researcher and engineer with interests spanning foundation models, computer vision, and responsible AI development. Passionate about bridging the gap between cutting-edge research and practical applications, with particular focus on efficiency, scalability, and ethical AI deployment.
Introducing LoongFlow: A Thinking & Learning Framework for Expert-Grade AI Agents.
Unlike traditional evolve agents(like OpenEvolve-Style), LoongFlow implements the PES (Plan-Execute-Summary) paradigm to learn from mistakes and avoid local optima.
š Highlights: * SOTA: Surpassed human mathematicians on 11 geometry/algebra problems. * 23 Kaggle Gold Medals on MLE Bench. * Efficiency: 60% more efficient than current baselines.