Yixiao Li

Unconstrained sampling offsets routinely degrade dynamic spatial modeling—freezing the kernel's center and filtering deformations with high-frequency edge priors consistently outperforms DCNv4 without adding architectural bloat.

Audio and acceleration modalities can predict physical interactions with surprising accuracy, but the executor's architecture is the true bottleneck in achieving effective multimodal execution.

ELMP slashes adaptation costs for motion planning by two orders of magnitude while boosting success rates in unseen environments to nearly 90%.

GSPan redefines pansharpening by leveraging continuous Gaussian representations, enabling high-quality image fusion across arbitrary scales without retraining.

Stop trading off fidelity for visual quality in super-resolution: a new network learns to directly optimize for human-preferred aesthetics.