Search papers, labs, and topics across Lattice.
6
15
5
9
CoCo achieves an 88.46% reduction in link utilization while effectively managing coherence overhead, revolutionizing many-core system optimization.
TECO achieves a groundbreaking balance between accuracy and efficiency by pruning CNNs across multiple dimensions, setting a new standard for embedded hardware performance.
Reducing ResNet-50's computational load by nearly 50% while boosting accuracy demonstrates a breakthrough in deploying CNNs on embedded devices.
Achieving over 100脳 reduction in computing power without sacrificing accuracy, this framework revolutionizes DNN inference on crossbar-based accelerators.
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.
