Resource-aware Pruning

Resource-Aware Pruning is a model compression technique that selectively removes parameters from neural networks based on an explicit optimization of computational, memory, or energy constraints to achieve efficient inference while preserving model performance.

47

Publications

3.2K

Citations

178

Authors

79

Institutions

Publications per year

2017–2026

44

Authors

178

  1. SH
    Song Han

    Massachusetts Institute of Technology, United States

    2 publications · 780 citations

    2

    h-index

  2. JY
    Jiahui Yu

    Zhejiang University, China

    2 publications · 180 citations

    2

    h-index

  3. PN
    Paul N. Whatmough

    American Rock Mechanics Association, United States

    2 publications · 132 citations

    2

    h-index

  4. IF
    Igor Fedorov

    Mid Sweden University, Sweden

    2 publications · 132 citations

    2

    h-index

  5. YW
    Yanzhi Wang

    Northeastern University, United States

    2 publications · 286 citations

    2

    h-index

1–5 of 178

Venues

  1. arXiv (Cornell University)

    Repository · 14 publications · 1.6K citations

    13

    h-index

  2. 3

    h-index

  3. IEEE Access

    3 publications · 92 citations

    3

    h-index

  4. 1

    h-index

  5. 1

    h-index

1–5