Zihan Liu

Achieving 18.5x faster city-scale 3D rendering on mobile VR devices while slashing energy consumption by 92.4% could redefine immersive experiences in urban environments.

Matching effective learning rates across different training setups leads to remarkably consistent loss trajectories, challenging conventional wisdom about learning rate variability.

FIBER achieves up to 2.25x speedup in LLM serving by decoupling tensor computation from register ownership, revolutionizing GPU efficiency.

Deltoris achieves a staggering 34.2× speedup for real-time VLA inference, revolutionizing how embodied AI can operate on edge devices.