Media Covergae

CoCoPIE: Compression-Compilation Co-Design for Real-Time Artificial Intelligence on Arbitrary Mobile Device (key conceptual paper here, demonstration paper here, Youtube channel here, Bilibili channel here)

  • “Yanzhi Wang Receives Army Young Investigator Award to Bring Deep Neural Network Machine Learning to Mobile Devices” reported in NEU News, also in Army Research Lab news.
  • “Developing AI Capabilities for Mobile Phones: Real-time 3D Action Recognition” reported by Medium.
  • “Software is still eating the world, even in the AI era” reported by Medium, and also in WebSystemerMC.AI.
  • “CoCoPIE: A software solution for putting real artificial intelligence in smaller spaces” reported in W&M News, also in TechXplore.
  • Reported in Xinzhiyuan (新智元), also cited in Tencent (腾讯快报), Sohu (搜狐).
  • Reported in Jiqizhixin (机器之心), also cited in Sina (新浪财经), (澎湃).

AutoCompress: Automatic DNN Structured Pruning for Ultra-High Compression Rates (paper here)

A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron Superconducting Technology (paper here)

Compression-Compiler Co-Optimization for Real-Time DNN Execution on General-Purpose Mobile Devices (paper here)

Speedup Up AI in USC Viterbi Communications.

Adversarial T-Shirt for Evading Real-Time Detection (paper here) (Over 200 media coverage on the web. A selected list in the following.)

Hierarchical Random Switching for DNN Robustness (paper here)

  • “How randomness can protect neural networks against adversarial attacks” by TechTalks
  • “Making neural networks robust with new perspective” by IBM Research Blog
  • “AI safety – how do you prevent adversarial attacks?” by Medium

Fingerprinting 3D Printers (paper here)

Block-Circulant based DNN Acceleration (paper here)