Yuan Wu

LASER cuts average latency by up to 38% while only sacrificing 1% accuracy, revolutionizing how we deploy reasoning models on edge devices.

Higher accuracy in vision-language models doesn't equate to greater robustness, especially when handling structured visual data.

RISE achieves a remarkable 2.1× speedup in text-to-image diffusion tasks by intelligently splitting the denoising workload between edge and device models without compromising quality.

AuRA achieves superior performance in speech-language tasks by seamlessly integrating audio understanding into LLMs, outperforming traditional methods in both speed and accuracy.

By intelligently incorporating LiDAR-derived height information, HiPR overcomes limitations of fixed projection spaces, achieving state-of-the-art camera-LiDAR occupancy prediction with real-time performance.