81 citations · 108 across the 29 of their papers we have counts for
9 papers · 1 filter
Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
Jeffrey Wang, Jonathan Gregory, Grigorios G. Chrysos
Modern vision backbones treat pointwise activations (e.g., ReLU, GELU) and exponential softmax as essential sources of nonlinearity, but we demonstrate they are not required within…
Mitigating Diffusion Model Hallucinations with Dynamic Guidance
Kostas Triaridis, Alexandros Graikos, Aggelina Chatziagapi +2
Hallucinations in diffusion models are samples with structural inconsistencies that can emerge due to the excessive smoothing of the learned score function, which in turn leads to…
The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
Daniel Morales-Brotons, Grigorios Chrysos, Stratis Tzoumas +1
Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To over…
MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
Aggelina Chatziagapi, Grigorios G. Chrysos, Dimitris Samaras
We introduce MIGS (Multi-Identity Gaussian Splatting), a novel method that learns a single neural representation for multiple identities, using only monocular videos. Recent 3D Gau…
PNeRV: A Polynomial Neural Representation for Videos
Sonam Gupta, Snehal Singh Tomar, Grigorios G Chrysos +2
Extracting Implicit Neural Representations (INRs) on video data poses unique challenges due to the additional temporal dimension. In the context of videos, INRs have predominantly…
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos +1
Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors l…
MI-NeRF: Learning a Single Face NeRF from Multiple Identities
Aggelina Chatziagapi, Grigorios G. Chrysos, Dimitris Samaras
In this work, we introduce a method that learns a single dynamic neural radiance field (NeRF) from monocular talking face videos of multiple identities. NeRFs have shown remarkable…
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos +5
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, a…
Multilinear Operator Networks
Yixin Cheng, Grigorios G. Chrysos, Markos Georgopoulos +1
Despite the remarkable capabilities of deep neural networks in image recognition, the dependence on activation functions remains a largely unexplored area and has yet to be elimina…