Skip to main content
← All research groups

Research group, D-21 PWr

genwro.AI

Leading generative models: diffusion, 3D, uncertainty and explainability.

  • generative models
  • diffusion models
  • computer vision
  • uncertainty modeling
  • model distillation
  • few-shot learning
  • 3D representations
  • NeRF
  • 3D Gaussian Splatting
  • super-resolution
  • image restoration
  • image colorization
  • instance segmentation
  • amodal segmentation
  • object detection
  • explainable AI
  • counterfactual explanations
  • machine unlearning
15
Members
6
Recent publications

Group leadership

Maciej ZiębaGroup head

Located

D-21 PWr

genwro.ai develops generative and diffusion models, computer vision, 3D representations, uncertainty modeling, distillation, few-shot learning, explainable AI and machine unlearning.

Members

15 members

Recent publications

  1. HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data

    Neurocomputing 2026 vol. 671, art. 132748, s. 1-11., 2026

  2. MultiPlaneNeRF: Neural radiance field with non-trainable representation

    Expert Systems with Applications 2025 vol. 279, art. 127350, s. 1-11. [ Publikacja zarejestrowana jako preonline dn. 31.03.2025, rok zaliczenia 2025. Wersja ostateczna zarejestrowana 30.06.2025, rok zaliczenia 2025.], 2025

  3. Direct detection of elongated objects geometry via a centerline-based representation

    Singapore : Springer Nature Singapore, cop. 2025. s. 75-88., 2025

  4. Joint MoE scaling laws: Mixture of Experts can be memory efficient

    [Cambridge, MA : JMLR, cop. 2025]. s. 1-18., 2025

  5. KeyFace: expressive audio-driven facial animation for long sequences via KeyFrame interpolation

    2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

  6. How to train your multi-exit model? Analyzing the impact of training strategies

    [Cambridge, MA : JMLR, cop. 2025]. s. 1-20., 2025