Pengcheng Li

An attribution gate precisely disentangles user intention from capability degradation in robotic assistance, achieving 3x lower trajectory error than prior methods.

Robots can now distinguish between a user who can't move and one who isn't paying attention, leading to more effective rehabilitation.

Fourier decomposition of motion enables unprecedented accuracy in rendering dynamic scenes, tackling the limitations of traditional polynomial models.

Unregistered WLI/NBI fusion can be reliably achieved by selectively integrating features based on their spatial correspondence, leading to superior lesion segmentation.

PoinTriE achieves state-of-the-art performance in point cloud video tasks while slashing memory requirements and annotation costs.

PIANO achieves a remarkable 4.45% increase in conversion rates by effectively aligning user intent with historical preferences in music search.