168 citations · 398 across the 15 of their papers we have counts for
15 papers
New Solutions on LLM Acceleration, Optimization, and Application
Yingbing Huang, Lily Jiaxin Wan, Hanchen Ye +5
Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. H…
SnapKV: LLM Knows What You are Looking for Before Generation
Yuhong Li, Yingbing Huang, Bowen Yang +6
Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. Howe…
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Tianle Cai, Yuhong Li, Zhengyang Geng +4
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as…
Extensible Proxy for Efficient NAS
Yuhong Li, Jiajie Li, Cong Han +3
Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are fur…
What Makes Convolutional Models Great on Long Sequence Modeling?
Yuhong Li, Tianle Cai, Yi Zhang +2
Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle long-range dependency ef…
Compilation and Optimizations for Efficient Machine Learning on Embedded Systems
Xiaofan Zhang, Yao Chen, Cong Hao +3
Deep Neural Networks (DNNs) have achieved great success in a variety of machine learning (ML) applications, delivering high-quality inferencing solutions in computer vision, natura…
Generic Neural Architecture Search via Regression
Yuhong Li, Cong Hao, Pan Li +2
Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive…
Effective Algorithm-Accelerator Co-design for AI Solutions on Edge Devices
Cong Hao, Yao Chen, Xiaofan Zhang +4
High quality AI solutions require joint optimization of AI algorithms, such as deep neural networks (DNNs), and their hardware accelerators. To improve the overall solution quality…
EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions
Yuhong Li, Cong Hao, Xiaofan Zhang +5
High quality AI solutions require joint optimization of AI algorithms and their hardware implementations. In this work, we are the first to propose a fully simultaneous, efficient…
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
Xiaofan Zhang, Haoming Lu, Cong Hao +9
Object detection and tracking are challenging tasks for resource-constrained embedded systems. While these tasks are among the most compute-intensive tasks from the artificial inte…
SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
Xiaofan Zhang, Cong Hao, Haoming Lu +9
Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding re…
A Bi-Directional Co-Design Approach to Enable Deep Learning on IoT Devices
Xiaofan Zhang, Cong Hao, Yuhong Li +4
Developing deep learning models for resource-constrained Internet-of-Things (IoT) devices is challenging, as it is difficult to achieve both good quality of results (QoR), such as…
FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge
Cong Hao, Xiaofan Zhang, Yuhong Li +5
While embedded FPGAs are attractive platforms for DNN acceleration on edge-devices due to their low latency and high energy efficiency, the scarcity of resources of edge-scale FPGA…
SiamVGG: Visual Tracking using Deeper Siamese Networks
Yuhong Li, Xiaofan Zhang, Deming Chen
Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlati…
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Yuhong Li, Xiaofan Zhang, Deming Chen
We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurat…