b'Song Han'

research

∙ 08/02/2022

PAN: Pulse Ansatz on NISQ Machines

Variational quantum algorithms (VQAs) have demonstrated great potentials...

Zhiding Liang, et al. ∙

research

∙ 07/13/2022

RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL

Analog/mixed-signal circuit design is one of the most complex and time-c...

Wei Shi, et al. ∙

research

∙ 06/30/2022

On-Device Training Under 256KB Memory

On-device training enables the model to adapt to new data collected from...

Ji Lin, et al. ∙

research

∙ 06/19/2022

MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue

Automatic open-domain dialogue evaluation is a crucial component of dial...

Pengfei Zhang, et al. ∙

research

∙ 05/29/2022

EfficientViT: Enhanced Linear Attention for High-Resolution Low-Computation Visual Recognition

Vision Transformer (ViT) has achieved remarkable performance in many vis...

Han Cai, et al. ∙

research

∙ 05/26/2022

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Multi-sensor fusion is essential for an accurate and reliable autonomous...

Zhijian Liu, et al. ∙

research

∙ 05/03/2022

Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

Pose estimation plays a critical role in human-centered vision applicati...

Yihan Wang, et al. ∙

research

∙ 04/25/2022

PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution

3D neural networks are widely used in real-world applications (e.g., AR/...

Zhijian Liu, et al. ∙

research

∙ 04/25/2022

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

Deep neural networks (DNNs) have achieved unprecedented success in the f...

Han Cai, et al. ∙

research

∙ 04/21/2022

TorchSparse: Efficient Point Cloud Inference Engine

Deep learning on point clouds has received increased attention thanks to...

Haotian Tang, et al. ∙

research

∙ 02/26/2022

QOC: Quantum On-Chip Training with Parameter Shift and Gradient Pruning

Parameterized Quantum Circuits (PQC) are drawing increasing research int...

Hanrui Wang, et al. ∙

research

∙ 12/27/2021

AET-SGD: Asynchronous Event-triggered Stochastic Gradient Descent

Communication cost is the main bottleneck for the design of effective di...

Nhuong Nguyen, et al. ∙

research

∙ 11/23/2021

VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles

Simulation has the potential to transform the development of robust algo...

Alexander Amini, et al. ∙

research

∙ 10/28/2021

MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

Tiny deep learning on microcontroller units (MCUs) is challenging due to...

Ji Lin, et al. ∙

research

∙ 10/21/2021

RoQNN: Noise-Aware Training for Robust Quantum Neural Networks

Quantum Neural Network (QNN) is a promising application towards quantum ...

Hanrui Wang, et al. ∙

research

∙ 10/17/2021

Network Augmentation for Tiny Deep Learning

We introduce Network Augmentation (NetAug), a new training method for im...

Han Cai, et al. ∙

research

∙ 10/14/2021

PointAcc: Efficient Point Cloud Accelerator

Deep learning on point clouds plays a vital role in a wide range of appl...

Yujun Lin, et al. ∙

research

∙ 09/27/2021

TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device

The explosive growth in video streaming requires video understanding at ...

Ji Lin, et al. ∙

research

∙ 08/26/2021

LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision

Computer vision tasks such as object detection and semantic/instance seg...

Zhijian Liu, et al. ∙

research

∙ 07/22/2021

QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits

Quantum noise is the key challenge in Noisy Intermediate-Scale Quantum (...

Hanrui Wang, et al. ∙

research

∙ 05/27/2021

NAAS: Neural Accelerator Architecture Search

Data-driven, automatic design space exploration of neural accelerator ar...

Yujun Lin, et al. ∙

research

∙ 05/20/2021

Efficient and Robust LiDAR-Based End-to-End Navigation

Deep learning has been used to demonstrate end-to-end neural network lea...

Zhijian Liu, et al. ∙

research

∙ 03/10/2021

PatchNet – Short-range Template Matching for Efficient Video Processing

Object recognition is a fundamental problem in many video processing tas...

Huizi Mao, et al. ∙

research

∙ 03/04/2021

Anycost GANs for Interactive Image Synthesis and Editing

Generative adversarial networks (GANs) have enabled photorealistic image...

Ji Lin, et al. ∙

research

∙ 12/17/2020

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

The attention mechanism is becoming increasingly popular in Natural Lang...

Hanrui Wang, et al. ∙

research

∙ 11/02/2020

IOS: Inter-Operator Scheduler for CNN Acceleration

To accelerate CNN inference, existing deep learning frameworks focus on ...

Yaoyao Ding, et al. ∙

research

∙ 08/11/2020

Hardware-Centric AutoML for Mixed-Precision Quantization

Model quantization is a widely used technique to compress and accelerate...

Kuan Wang, et al. ∙

research

∙ 07/31/2020

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Self-driving cars need to understand 3D scenes efficiently and accuratel...

Haotian Tang, et al. ∙

research

∙ 07/22/2020

Tiny Transfer Learning: Towards Memory-Efficient On-Device Learning

We present Tiny-Transfer-Learning (TinyTL), an efficient on-device learn...

Han Cai, et al. ∙

research

∙ 07/20/2020

MCUNet: Tiny Deep Learning on IoT Devices

Machine learning on tiny IoT devices based on microcontroller units (MCU...

Ji Lin, et al. ∙

research

∙ 06/18/2020

Differentiable Augmentation for Data-Efficient GAN Training

The performance of generative adversarial networks (GANs) heavily deteri...

Shengyu Zhao, et al. ∙

research

∙ 06/15/2020

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

We present APQ for efficient deep learning inference on resource-constra...

Tianzhe Wang, et al. ∙

research

∙ 05/28/2020

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, ...

Hanrui Wang, et al. ∙

research

∙ 05/16/2020

MicroNet for Efficient Language Modeling

It is important to design compact language models for efficient deployme...

Zhongxia Yan, et al. ∙

research

∙ 04/30/2020

GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning

Automatic transistor sizing is a challenging problem in circuit design d...

Hanrui Wang, et al. ∙

research

∙ 04/24/2020

Lite Transformer with Long-Short Range Attention

Transformer has become ubiquitous in natural language processing (e.g., ...

Zhanghao Wu, et al. ∙

research

∙ 04/12/2020

A Fast Algorithm for Source-Wise Round-Trip Spanners

In this paper, we study the problem of efficiently constructing source-w...

Chun Jiang Zhu, et al. ∙

research

∙ 03/19/2020

GAN Compression: Efficient Architectures for Interactive Conditional GANs

Conditional Generative Adversarial Networks (cGANs) have enabled control...

Muyang Li, et al. ∙

research

∙ 02/20/2020

SpArch: Efficient Architecture for Sparse Matrix Multiplication

Generalized Sparse Matrix-Matrix Multiplication (SpGEMM) is a ubiquitous...

Zhekai Zhang, et al. ∙

research

∙ 10/02/2019

ChainSplitter: Towards Blockchain-based Industrial IoT Architecture for Supporting Hierarchical Storage

The fast developing Industrial Internet of Things (IIoT) technologies pr...

Gang Wang, et al. ∙

research

∙ 10/01/2019

Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos

Deep video recognition is more computationally expensive than image reco...

Ji Lin, et al. ∙

research

∙ 08/26/2019

Once for All: Train One Network and Specialize it for Efficient Deployment

Efficient deployment of deep learning models requires specialized neural...

Han Cai, et al. ∙

research

∙ 07/08/2019

Point-Voxel CNN for Efficient 3D Deep Learning

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning....

Zhijian Liu, et al. ∙

research

∙ 06/21/2019

Deep Leakage from Gradients

Exchanging gradients is a widely used method in modern multi-node machin...

Ligeng Zhu, et al. ∙

research

∙ 04/24/2019

Design Automation for Efficient Deep Learning Computing

Efficient deep learning computing requires algorithm and hardware co-des...

Song Han, et al. ∙

research

∙ 04/17/2019

Defensive Quantization: When Efficiency Meets Robustness

Neural network quantization is becoming an industry standard to efficien...

Ji Lin, et al. ∙

research

∙ 03/29/2019

SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...

Alexander Ratner, et al. ∙

research

∙ 02/06/2019

Fully Distributed Packet Scheduling Framework for Handling Disturbances in Lossy Real-Time Wireless Networks

Along with the rapid growth of Industrial Internet-of-Things (IIoT) appl...

Tianyu Zhang, et al. ∙

research

∙ 12/05/2018

Learning to Design Circuits

Analog IC design relies on human experts to search for parameters that s...

Hanrui Wang, et al. ∙

research

∙ 12/02/2018

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Neural architecture search (NAS) has a great impact by automatically des...

Han Cai, et al. ∙

Song Han

Featured Co-authors