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

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

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

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

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

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

[ICML'21 Oral] I-BERT: Integer-only BERT Quantization

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

Efficient 3D Backbone Network for Temporal Modeling

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2

[KDD'22] Learned Token Pruning for Transformers

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

Any-Precision Deep Neural Networks (AAAI 2021)

Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models".

[JMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion

[MICCAI 2021] BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation

Concise, Modular, Human-friendly PyTorch implementation of EfficientNet with Pre-trained Weights.