8 citations · 15 across the 10 of their papers we have counts for
12 papers
Multimodal Co-Generation With Continuous Bitstream Diffusion
Georgios Batzolis, Georgios Kontos, Bruno Trentini +4
We show that continuous bitstream diffusion (CoBit), originally developed for language modeling, provides a unified framework for joint and conditional multimodal generation using…
Beyond Unimodal Bases: Pullback Geometry for Multimodal Data
Honglei Brinkmann, Lucas Ng, Georgios Batzolis +3
Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high-dimensional data. For these operations to be statistically meaningful, paths…
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
Luca Ambrogioni, Giulio Franzese, Alberto Foresti +7
How should a diffusion model decide which noise levels to train on, and how much? Despite the importance of this choice, current noise schedules are based largely on heuristics or…
CoBit: Language Modeling with Bitstream Diffusion
Georgios Batzolis, Mark Girolami, Luca Ambrogioni
Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample qualit…
Noise Scheduling as Information-Guided Allocation in Diffusion Training
Gabriel Raya, Bac Nguyen, Georgios Batzolis +6
We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels where denoising is most informative. Toget…
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
Willem Diepeveen, Georgios Batzolis, Zakhar Shumaylov +1
Data-driven Riemannian geometry has emerged as a powerful tool for interpretable representation learning, offering improved efficiency in downstream tasks. Moving forward, it is cr…
Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb
As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeabl…
Your diffusion model secretly knows the dimension of the data manifold
Jan Stanczuk, Georgios Batzolis, Teo Deveney +1
In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e.…
Non-Uniform Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb +1
Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show…
Conditional Image Generation with Score-Based Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb +1
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical ana…
CAFLOW: Conditional Autoregressive Flows
Georgios Batzolis, Marcello Carioni, Christian Etmann +3
We introduce CAFLOW, a new diverse image-to-image translation model that simultaneously leverages the power of auto-regressive modeling and the modeling efficiency of conditional n…
How to distribute data across tasks for meta-learning?
Alexandru Cioba, Michael Bromberg, Qian Wang +5
Meta-learning models transfer the knowledge acquired from previous tasks to quickly learn new ones. They are trained on benchmarks with a fixed number of data points per task. This…