Qian Lin

Reward functions that generalize across environments can be learned more effectively by strategically leveraging heterogeneous feedback modalities, leading to substantial improvements in agent performance.

FedTR achieves 95.5% accuracy in label defect identification, rivaling centralized models while preserving data privacy in federated learning settings.

Reducing ResNet-50's computational load by nearly 50% while boosting accuracy demonstrates a breakthrough in deploying CNNs on embedded devices.

Achieving over 100× reduction in computing power without sacrificing accuracy, this framework revolutionizes DNN inference on crossbar-based accelerators.

Achieving real-time performance on edge devices, this method reduces GoogLeNet's latency from 40.32 ms to 34 ms with minimal accuracy loss, while VGG-19 sees a latency drop from 119.98 ms to 34 ms with an accuracy gain.

Smart Scissor reduces CNN computational costs by over 40% while actually improving accuracy, challenging the notion that efficiency comes at the expense of performance.

Heterogeneous models can be collaboratively trained to improve accuracy under strict latency constraints, achieving significant performance gains without extra training costs.