Shi Fu

Online submodular optimization cannot match the classic $1-1/e$ guarantee under stable updates: beating $2-\sqrt{2} \approx 0.5858$ provably triggers either an exponential query explosion or catastrophic $\Omega(k)$ recourse per step.

Heavy-tailed designs can lead to a dramatic increase in sample complexity, challenging established norms in statistical recovery.

Nuisance interpolation in feature priming can lead to significant underperformance in online regression, revealing a fundamental limitation in existing regret guarantees.

ACE-Brain-0.5 unifies spatial reasoning and action generation in embodied AI, achieving remarkable performance improvements across multiple benchmarks.

Kairos achieves top-tier performance in Physical AI while ensuring efficient state management over extended time horizons, setting a new standard for operational world models.