Nikos Komodakis

7

Papers

86

Total Citations

Papers (7)

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

DINO-Foresight: Looking into the Future with DINO

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

Multi-Token Prediction Needs Registers

NeurIPS 2025arXiv

ToNNO: Tomographic Reconstruction of a Neural Network’s Output for Weakly Supervised Segmentation of 3D Medical Images

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers