Tiny Machine Learning: Progress and Futures

1 code implementation • 28 Mar 2024 • Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang, Song Han

By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of AI applications and enable ubiquitous intelligence.

PockEngine: Sparse and Efficient Fine-tuning in a Pocket

no code implementations • 26 Oct 2023 • Ligeng Zhu, Lanxiang Hu, Ji Lin, Wei-Chen Wang, Wei-Ming Chen, Chuang Gan, Song Han

On-device learning and efficient fine-tuning enable continuous and privacy-preserving customization (e. g., locally fine-tuning large language models on personalized data).

Privacy Preserving

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

5 code implementations • 1 Jun 2023 • Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han

We then propose to search for the optimal per-channel scaling that protects the salient weights by observing the activation, not weights.

Autonomous Driving Common Sense Reasoning +3

Detecting Label Errors in Token Classification Data

2 code implementations • 8 Oct 2022 • Wei-Chen Wang, Jonas Mueller

Mislabeled examples are a common issue in real-world data, particularly for tasks like token classification where many labels must be chosen on a fine-grained basis.

General Classification Token Classification

On-Device Training Under 256KB Memory

1 code implementation • 30 Jun 2022 • Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han

To reduce the memory footprint, we propose Sparse Update to skip the gradient computation of less important layers and sub-tensors.

Quantization Transfer Learning