7 papers
Coevolving Representations in Joint Image-Feature Diffusion
Theodoros Kouzelis, Spyros Gidaris, Nikos Komodakis
Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic fe…
Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency
Bill Psomas, Dionysis Christopoulos, Eirini Baltzi +6
As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whos…
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Theodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou +2
Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel ge…
DINO-Foresight: Looking into the Future with DINO
Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris +1
Predicting future dynamics is crucial for applications like autonomous driving and robotics, where understanding the environment is key. Existing pixel-level methods are computatio…
Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris +1
Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction t…
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Theodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris +1
Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed b…