About

Patrick Huang, PT, DPT, OCS, CSCS, is an Assistant Professor of Clinical Physical Therapy at the USC Division of Biokinesiology and Physical Therapy. He practices at USC Physical Therapy at the University Park Campus, specializing in the management of orthopedic conditions. Dr. Huang is a board certified orthopedic clinical specialist and serves as a mentor and clinical instructor to entry-level doctoral students in USC’s Physical Therapy program. His professional interests include orthopedic rehabilitation, and he is a member of the American Physical Therapy Association and the Academy of Orthopaedic Physical Therapy. He completed his Orthopedic Physical Therapy Residency at the University of Southern California in 2019, earned his Doctor of Physical Therapy from USC in 2018, and holds a Bachelor of Science in Physiological Sciences from UCLA obtained in 2014.

Research topics

• Computer Science
• Composite material
• Chemistry
• Simulation
• Distributed computing
• Optics
• Algorithm
• Physics
• Mechanics
• Engineering
• Geology
• Classical mechanics
• Geometry
• Mathematics
• Computer network
• Real-time computing
• Materials science

Selected publications

• Edge LLM Inference on Big.LITTLE Architectures

  2026-03-28

  article

  Recent edge devices are equipped with multiple high-performance processor cores, which are capable of edge LLM inference. Heterogeneous multicores with both performance- and efficiency- (i.e., less-performance but very power-efficient) processor cores are common for tasks with varying workloads to save energy, but they create hurdles for parallel LLM computing. This paper presents core streamlining, fined-grained multithreading, and computility-aware multithreading to improve the performance of edge LLM on heterogeneous multicores. In our experiments, the inference of Llama3 8B on an 8core SoC (RK3588) has been improved from 2.12 tokens/s to 3. 9 6, ~4. 1 3 and 4. 8 5 respectively.

  PublisherDOI

• Human 3D mesh reconstruction from single RGB image based on deep learning network

  2025-02-05

  articleSenior author
  PublisherDOI

• Multiple temporal scale network for remote PPG and heart rate estimation from facial video

  Biomedical Signal Processing and Control · 2025-07-15

  article
  PublisherDOI

• fMRI Activity Slop Feature with Poincare Plot for Emotion Classification

  World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · 2025-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

• Efficient Inference of Transformers on Bare-Metal Devices with RISC-V Vector Processors

  2024-06-16

  article

  Most neural network frameworks have only limited supports for bare-metal devices, where specific primitives need considering and hand optimizations for such devices incur a substantial development cost. This paper presents an efficient workflow using PyTorch Transformer, where a RISC-V device is used as an example. Models from different frameworks can be efficiently deployed and optimized, where bottlenecks are segmented and optimized using intricsic instructions. Moreever, TVM BYOC (Bring Your Own Codegen) has been adopted for custom optimizations.

  PublisherDOI

• A Two-Stream Deep-Learning Network for Heart Rate Estimation From Facial Image Sequence

  IEEE Sensors Journal · 2024-10-24 · 2 citations

  article

  This article presents a deep-learning-based two-stream network to estimate remote Photoplethysmogram (rPPG) signal and hence derive the heart rate (HR) from an RGB facial video. Our proposed network employs temporal modulation blocks (TMBs) to efficiently extract temporal dependencies and spatial attention blocks on a mean frame to learn spatial features. Our TMBs are composed of two subblocks that can simultaneously learn overall and channelwise spatiotemporal features, which are pivotal for the task. Data augmentation (DA) in training and multiple redundant estimations for noise removal in testing were also designed to make the training more effective and the inference more robust. Experimental results show that the proposed temporal shift-channelwise spatio-temporal network (TS-CST Net) has reached competitive and even superior performances among the state-of-the-art (SOTA) methods on four popular datasets, showcasing our network’s learning capability.

  PublisherDOI

• DEFAEK: Domain Effective Fast Adaptive Network for Face Anti-Spoofing

  Neural Networks · 2023-01-25 · 12 citations

  article
  PublisherDOI

• AutoCast

  2022 · 51 citations

  • Computer Science
  • Computer Science
  • Distributed computing

  Autonomous vehicles use 3D sensors for perception. Cooperative perception enables vehicles to share sensor readings with each other to improve safety. Prior work in cooperative perception scales poorly even with infrastructure support. AUTOCAST1 enables scalable infrastructure-less cooperative perception using direct vehicle-to-vehicle communication. It carefully determines which objects to share based on positional relationships between traffic participants, and the time evolution of their trajectories. It coordinates vehicles and optimally schedules transmissions in a distributed fashion. Extensive evaluation results under different scenarios show that, unlike competing approaches, AUTOCAST can avoid crashes and near-misses which occur frequently without cooperative perception, its performance scales gracefully in dense traffic scenarios providing 2-4x visibility into safety critical objects compared to existing cooperative perception schemes, its transmission schedules can be completed on the real radio testbed, and its scheduling algorithm is near-optimal with negligible computation overhead.

  PublisherOA PDFDOI

• Analytics and Machine Learning Powered Wireless Network Optimization and Planning

  arXiv (Cornell University) · 2022-09-14

  preprintOpen accessSenior author

  It is important that the wireless network is well optimized and planned, using the limited wireless spectrum resources, to serve the explosively growing traffic and diverse applications needs of end users. Considering the challenges of dynamics and complexity of the wireless systems, and the scale of the networks, it is desirable to have solutions to automatically monitor, analyze, optimize, and plan the network. This article discusses approaches and solutions of data analytics and machine learning powered optimization and planning. The approaches include analyzing some important metrics of performances and experiences, at the lower layers and upper layers of open systems interconnection (OSI) model, as well as deriving a metric of the end user perceived network congestion indicator. The approaches include monitoring and diagnosis such as anomaly detection of the metrics, root cause analysis for poor performances and experiences. The approaches include enabling network optimization with tuning recommendations, directly targeting to optimize the end users experiences, via sensitivity modeling and analysis of the upper layer metrics of the end users experiences v.s. the improvement of the lower layers metrics due to tuning the hardware configurations. The approaches also include deriving predictive metrics for network planning, traffic demand distributions and trends, detection and prediction of the suppressed traffic demand, and the incentives of traffic gains if the network is upgraded. These approaches of optimization and planning are for accurate detection of optimization and upgrading opportunities at a large scale, enabling more effective optimization and planning such as tuning cells configurations, upgrading cells capacity with more advanced technologies or new hardware, adding more cells, etc., improving the network performances and providing better experiences to end users.

  PublisherOA PDFDOI

• Research on size segregation dynamics and processes of a binary mixture dense granular flow

  Minerals Engineering · 2022 · 9 citations

  • Mechanics
  • Materials science
  • Physics
  PublisherDOI

Frequent coauthors

• Konstantinos Psounis

  10 shared

• Hsien-Ching Hsieh

  Industrial Technology Research Institute

  7 shared

• Yue-Hua Han

  Research Center for Information Technology Innovation, Academia Sinica

  5 shared

• Huang-Lun Lin

  Industrial Technology Research Institute

  5 shared

• Christopher J. Forster

  4 shared

• Namo Asavisanu

  Southern California University for Professional Studies

  4 shared

• Wanjiun Liao

  National Taiwan University

  4 shared

• Hang Qiu

  University of California, Riverside

  4 shared

Labs

• Health Equity LabPI

Education

• Other, Physical Therapy

  University of Southern California