[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 2…

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

[SIGMOD 2023] High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.