Markos Georgopoulos
YOU?
Author Swipe
View article: Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
Improving Chain-of-Thought Efficiency for Autoregressive Image Generation Open
Autoregressive multimodal large language models have recently gained popularity for image generation, driven by advances in foundation models. To enhance alignment and detail, newer approaches employ chain-of-thought (CoT) reasoning, expan…
View article: GGHead: Fast and Generalizable 3D Gaussian Heads
GGHead: Fast and Generalizable 3D Gaussian Heads Open
Learning 3D head priors from large 2D image collections is an important step towards high-quality 3D-aware human modeling. A core requirement is an efficient architecture that scales well to large-scale datasets and large image resolutions…
View article: Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization Open
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, and editability. However, a major challenge lies in the comp…
View article: Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks Open
Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly …
View article: Multilinear Operator Networks
Multilinear Operator Networks Open
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 eliminated. On the other hand, Polynomial Networks is a class of m…
View article: MonoNPHM: Dynamic Head Reconstruction from Monocular Videos
MonoNPHM: Dynamic Head Reconstruction from Monocular Videos Open
We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos. To this end, we propose a latent appearance space that parameterizes a texture field on top of a neural parametric…
View article: KAN-AV dataset for audio-visual face and speech analysis in the wild
KAN-AV dataset for audio-visual face and speech analysis in the wild Open
Human-computer interaction is becoming increasingly prevalent in daily life with the adoption of intelligent devices. These devices must be capable of interacting in diverse settings, such as environments with noise, music and differing il…
View article: HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion Open
Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the gap to production-level quality, we introduce HumanRF 1 , a …
View article: Learning Neural Parametric Head Models
Learning Neural Parametric Head Models Open
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles identity and expressions in disjoint latent spaces. To this en…
View article: Cluster-guided Image Synthesis with Unconditional Models
Cluster-guided Image Synthesis with Unconditional Models Open
Generative Adversarial Networks (GANs) are the driving force behind the state-of-the-art in image generation. Despite their ability to synthesize high-resolution photo-realistic images, generating content with on-demand conditioning of dif…
View article: Tensor Component Analysis for Interpreting the Latent Space of GANs
Tensor Component Analysis for Interpreting the Latent Space of GANs Open
This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis. Such interpretable directions correspond to transfor…
View article: Tensor Component Analysis for Interpreting the Latent Space of GANs
Tensor Component Analysis for Interpreting the Latent Space of GANs Open
This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis. Such interpretable directions correspond to transfor…
View article: Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer
Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer Open
Deep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard eva…
View article: Augmenting Deep Classifiers with Polynomial Neural Networks
Augmenting Deep Classifiers with Polynomial Neural Networks Open
Deep neural networks have been the driving force behind the success in classification tasks, e.g., object and audio recognition. Impressive results and generalization have been achieved by a variety of recently proposed architectures, the …
View article: Polynomial Networks in Deep Classifiers.
Polynomial Networks in Deep Classifiers. Open
Deep neural networks have been the driving force behind the success in classification tasks, e.g., object and audio recognition. Impressive results and generalization have been achieved by a variety of recently proposed architectures, the …
View article: CoPE: Conditional image generation using Polynomial Expansions
CoPE: Conditional image generation using Polynomial Expansions Open
Generative modeling has evolved to a notable field of machine learning. Deep polynomial neural networks (PNNs) have demonstrated impressive results in unsupervised image generation, where the task is to map an input vector (i.e., noise) to…
View article: Multilinear Latent Conditioning for Generating Unseen Attribute Combinations
Multilinear Latent Conditioning for Generating Unseen Attribute Combinations Open
Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images. However, empirical studies have shown that variational autoencoders (VAE) and generative adv…
View article: Multilinear Latent Conditioning for Generating Unseen Attribute Combinations
Multilinear Latent Conditioning for Generating Unseen Attribute Combinations Open
Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images. However, empirical studies have shown that variational autoencoders (VAE) and generative adv…
View article: Enhancing Facial Data Diversity with Style-based Face Aging
Enhancing Facial Data Diversity with Style-based Face Aging Open
A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to alg…
View article: Investigating Bias in Deep Face Analysis: The KANFace Dataset and\n Empirical Study
Investigating Bias in Deep Face Analysis: The KANFace Dataset and\n Empirical Study Open
Deep learning-based methods have pushed the limits of the state-of-the-art in\nface analysis. However, despite their success, these models have raised\nconcerns regarding their bias towards certain demographics. This bias is\ninflicted bot…
View article: Modeling of Facial Aging and Kinship: A Survey
Modeling of Facial Aging and Kinship: A Survey Open
Computational facial models that capture properties of facial cues related to aging and kinship increasingly attract the attention of the research community, enabling the development of reliable methods for age progression, age estimation,…
View article: Modelling of Facial Aging and Kinship: A Survey
Modelling of Facial Aging and Kinship: A Survey Open
Computational facial models that capture properties of facial cues related to aging and kinship increasingly attract the attention of the research community, enabling the development of reliable methods for age progression, age estimation,…