Controllable Generation

Controllable Generation is a generative modeling framework that enables explicit manipulation of specific attributes or features in the output by conditioning the generation process on user-defined control signals.

207

Publications

14.9K

Citations

841

Authors

265

Institutions

Publications per year

2017–2026

156

Authors

841

  1. YC
    Yejin Choi

    University of Washington, United States

    5 publications · 208 citations

    5

    h-index

  2. XL
    Xiaodan Liang

    Sun Yat-sen University, China

    4 publications · 282 citations

    4

    h-index

  3. EP
    Eric P. Xing

    Carnegie Mellon University, United States

    4 publications · 282 citations

    4

    h-index

  4. MS
    Maarten Sap

    University of Washington, United States

    4 publications · 124 citations

    4

    h-index

  5. YD
    Yury Dvorkin

    New York University, United States

    4 publications · 461 citations

    4

    h-index

1–5 of 841

Venues

  1. arXiv (Cornell University)

    Repository · 51 publications · 2.8K citations

    24

    h-index

  2. Lab on a Chip

    4 publications · 145 citations

    4

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 959 citations

    4

    h-index

  4. IEEE Transactions on Power Systems

    4 publications · 448 citations

    4

    h-index

  5. Physical Review A

    PRA · 3 publications · 62 citations

    3

    h-index

1–5