270 citations · 866 across the 15 of their papers we have counts for
15 papers
Tiny Machine Learning: Progress and Futures
Ji Lin, Ligeng Zhu, Wei-Ming Chen +2
Tiny Machine Learning (TinyML) is a new frontier of machine learning. By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scop…
VILA: On Pre-training for Visual Language Models
Ji Lin, Hongxu Yin, Wei Ping +7
Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM wi…
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
Ligeng Zhu, Lanxiang Hu, Ji Lin +4
On-device learning and efficient fine-tuning enable continuous and privacy-preserving customization (e.g., locally fine-tuning large language models on personalized data). However,…
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
Ji Lin, Wei-Ming Chen, Han Cai +2
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in…
Network Augmentation for Tiny Deep Learning
Han Cai, Chuang Gan, Ji Lin +1
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation…
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
Ji Lin, Chuang Gan, Kuan Wang +1
The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture te…
Anycost GANs for Interactive Image Synthesis and Editing
Ji Lin, Richard Zhang, Frieder Ganz +2
Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing. However, due to the high computational cost of large-scale generators (e.g., StyleGA…
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Haotian Tang, Zhijian Liu, Shengyu Zhao +4
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able…
Hardware-Centric AutoML for Mixed-Precision Quantization
Kuan Wang, Zhijian Liu, Yujun Lin +2
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1…
MCUNet: Tiny Deep Learning on IoT Devices
Ji Lin, Wei-Ming Chen, Yujun Lin +3
Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than…
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
Tianzhe Wang, Kuan Wang, Han Cai +3
We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and q…
Differentiable Augmentation for Data-Efficient GAN Training
Shengyu Zhao, Zhijian Liu, Ji Lin +2
The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the e…
Lite Transformer with Long-Short Range Attention
Zhanghao Wu, Zhijian Liu, Ji Lin +2
Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve hi…
GAN Compression: Efficient Architectures for Interactive Conditional GANs
Muyang Li, Ji Lin, Yaoyao Ding +3
Conditional Generative Adversarial Networks (cGANs) have enabled controllable image synthesis for many vision and graphics applications. However, recent cGANs are 1-2 orders of mag…
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
Ji Lin, Chuang Gan, Song Han
Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential…