20 open source projects by mit-han-lab

[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

[ACL 2020] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

A high-performance neural network library for point cloud processing.

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

[NeurIPS 2019] Deep Leakage From Gradients

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

[LPIRC 2019] First place in the Visual Wake Words challenge (TF-lite track)

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

[ICLR 2020] Lite Transformer with Long-Short Range Attention

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

Efficient 3D Deep Learning

Binary Neural Network on IceStick FPGA.