Hi, I am Kai Huang, currently a PhD candidate at the Department of Electrical and Computer Engineering, University of Pittsburgh. I have broad interests in Efficient AI and AI for Systems.

Here is my CV. My research aims to enable efficient inference and fine-tuning of AI models, which can be particularly useful on resource-constrained devices, e.g., MCU boards, Raspberry Pi, and Nvidia Jetson. My early study focused on AI for wireless communication, where I designed modular and lightweight AI models to enhance the performance of wireless communication systems (e.g., WiFi and backscatter). Later I started to work on On-Device AI, where I optimized the inference and training cost of AI models on weak embedded devices. Overall my research involves not only traditional AI models (e.g., MLP and CNN), but also large generative models, such as large language models, diffusion models, and large multimodal models. Recently I made a subjective roadmap for Generative AI.

Publications

[arXiv] Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI
Kai Huang, Boyuan Yang, Wei Gao
arXiv preprint 2023
[paper] [code]

[ICLR’24] Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
Kai Huang, Hanyun Yin, Heng Huang, Wei Gao
The Twelfth International Conference on Learning Representations
Acceptance Ratio: 2250/7304=30.8%
[paper] [talk] [code]

[MobiSys’23] ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
Kai Huang, Boyuan Yang, Wei Gao
Proceedings of the 21st International Conference on Mobile Systems, Applications, and Services
Acceptance Ratio: 41/198=20.7%
🎉 Received ACM Artifact Available, Functional, Reusable, Results Replicated Badges (4/17)
[paper] [slides] [teaser] [code]

[MobiSys’23] PTEase: Objective Airway Examination for Pulmonary Telemedicine using Commodity Smartphones
Xiangyu Yin, Kai Huang, Erick Forno, Wei Chen, Heng Huang, Wei Gao
Proceedings of the 21st International Conference on Mobile Systems, Applications, and Services
Acceptance Ratio: 41/198=20.7%
[paper] [teaser] [code]

[MobiCom’22] Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
Kai Huang, Wei Gao
The 28th Annual International Conference On Mobile Computing And Networking
Acceptance Ratio: 56/314=17.8%
[paper] [slides] [talk] [code]

[IoTDI’22] RAScatter: Achieving Energy-Efficient Backscatter Readers via AI-Assisted Power Adaptation
Kai Huang, Ruirong Chen, Wei Gao
The 7th ACM/IEEE Conference on Internet of Things Design and Implementation
Acceptance Ratio: 12/36=33.3%
[paper] [slides] [code]

[SenSys’22] AiFi: AI-Enabled WiFi Interference Cancellation with Commodity PHY-Layer Information
Ruirong Chen, Kai Huang, Wei Gao
Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems
Acceptance Ratio: 52/209=24.8%
[paper] [slides] [code]

[CML-IOT’22] Out-Clinic Pulmonary Disease Evaluation via Acoustic Sensing and Multi-Task Learning on Commodity Smartphones
Xiangyu Yin, Kai Huang, Erick Forno, Wei Chen, Heng Huang, Wei Gao
The Fourth Workshop on Continual and Multimodal Learning for Internet of Things
🎉 Best Paper Award
[paper]

[IPSN’22] FaceListener: Recognizing Human Facial Expressions via Acoustic Sensing on Commodity Headphones
Xingzhe Song, Kai Huang, Wei Gao
21st ACM/IEEE International Conference on Information Processing in Sensor Networks
Acceptance Ratio: 38/126=30.2%
[paper]

[ASPLOS’22] Eavesdropping user credentials via GPU side channels on smartphones
Boyuan Yang, Ruirong Chen, Kai Huang, Jun Yang, Wei Gao
Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
Acceptance Ratio: 80/397=20.2%
[paper] [talk] [code]

[MobiSys’20] MagHacker: eavesdropping on stylus pen writing via magnetic sensing from commodity mobile devices
Yihao Liu*, Kai Huang*, Xingzhe Song, Boyuan Yang, Wei Gao
* indicates equal contributions
Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
Acceptance Ratio: 34/175=19.4%
[paper]

Education

• Ph.D. student, Electrical and Computer Engineering, University of Pittsburgh, On-going
• B.E., Electronic Information Engineering, University of Science and Technology of China (USTC), Sept. 2015 - July 2019

Latest News

• [1/2024] Our paper “Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation” got accepted to ICLR 2024!
• [11/2023] Our paper “Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI” is on arXiv!
• [9/2023] Our paper “Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation” is on arXiv!
• [5/2023] ElasticTrainer got awarded ACM Artifact Available, Functional, Reusable, Results Replicated Badges (4 out of 17 artifacts)!
• [2/2023] Two papers got conditionally accepted to The 21st ACM International Conference on Mobile Systems, Applications, and Services (MobiSys) 2023!
• [10/2022] One paper got accepted to The 20th ACM Conference on Embedded Networked Sensor Systems (SenSys) 2022!
• [6/2022] One paper got accepted to The 28th Annual International Conference on Mobile Computing and Networking (MobiCom) 2022!
• [1/2022] One paper got accepted to The 7th ACM/IEEE International Conference on Internet of Things Design and Implementation (IoTDI) 2022!
• [1/2022] One paper got accepted to The 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) 2022!
• [11/2021] One paper got accepted to Proceedings of the 27th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2022!
• [3/2020] One paper got accepted to The 18th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys) 2020!

Visitors