Auguste Genovesio
YOU?
Author Swipe
View article: Multi-marginal temporal Schrödinger Bridge Matching from unpaired data
Multi-marginal temporal Schrödinger Bridge Matching from unpaired data Open
Many natural dynamic processes -- such as in vivo cellular differentiation or disease progression -- can only be observed through the lens of static sample snapshots. While challenging, reconstructing their temporal evolution to decipher u…
View article: The 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real): Methods and Results
The 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real): Methods and Results Open
This paper reviews the 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real), held in conjunction with ICCV 2025. The workshop aimed to bridge the gap between the theoretical promise of D…
View article: DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization
DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization Open
Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. We introduce DiViD, …
View article: A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features
A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features Open
Understanding cellular responses to stimuli is crucial for biological discovery and drug development. Transcriptomics provides interpretable, gene-level insights, while microscopy imaging offers rich predictive features but is harder to in…
View article: Large Scale Cell Painting Guided Compound Selection Reveals Activity Cliffs and Functional Relationships
Large Scale Cell Painting Guided Compound Selection Reveals Activity Cliffs and Functional Relationships Open
Traditional structure-based pre-screen compound selection relies on the assumption that chemical similarity implies similar biological activity. This paradigm narrows the exploration of chemical space and often fails to account for functio…
View article: In vivo autofluorescence lifetime imaging of the Drosophila brain captures metabolic shifts associated with memory formation
In vivo autofluorescence lifetime imaging of the Drosophila brain captures metabolic shifts associated with memory formation Open
Neuronal energy regulation is increasingly recognized as a critical factor underlying brain functions and their pathological alterations, yet the metabolic dynamics that accompany cognitive processes remain poorly understood. As a label-fr…
View article: In vivo autofluorescence lifetime imaging of the Drosophila brain captures metabolic shifts associated with memory formation
In vivo autofluorescence lifetime imaging of the Drosophila brain captures metabolic shifts associated with memory formation Open
Neuronal energy regulation is increasingly recognized as a critical factor underlying brain functions and their pathological alterations, yet the metabolic dynamics that accompany cognitive processes remain poorly understood. As a label-fr…
View article: Revealing Subtle Phenotypes in Small Microscopy Datasets Using Latent Diffusion Models
Revealing Subtle Phenotypes in Small Microscopy Datasets Using Latent Diffusion Models Open
Identifying subtle phenotypic variations in cellular images is critical for advancing biological research and accelerating drug discovery. These variations are often masked by the inherent cellular heterogeneity, making it challenging to d…
View article: DiffEx: Explaining a Classifier with Diffusion Models to Identify Microscopic Cellular Variations
DiffEx: Explaining a Classifier with Diffusion Models to Identify Microscopic Cellular Variations Open
In recent years, deep learning models have been extensively applied to biological data across various modalities. Discriminative deep learning models have excelled at classifying images into categories (e.g., healthy versus diseased, treat…
View article: In vivo autofluorescence lifetime imaging of spatial metabolic heterogeneities and learning-induced changes in the <i>Drosophila</i> mushroom body
In vivo autofluorescence lifetime imaging of spatial metabolic heterogeneities and learning-induced changes in the <i>Drosophila</i> mushroom body Open
Neuronal energy regulation is increasingly recognized as a critical factor underlying brain functions and their pathological alterations, yet the metabolic dynamics that accompany cognitive processes remain poorly understood. As a label-fr…
View article: GANs Conditioning Methods: A Survey
GANs Conditioning Methods: A Survey Open
In recent years, Generative Adversarial Networks (GANs) have seen significant advancements, leading to their widespread adoption across various fields. The original GAN architecture enables the generation of images without any specific con…
View article: Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search
Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search Open
Supervised deep learning approaches can artificially increase the resolution of microscopy images by learning a mapping between two image resolutions or modalities. However, such methods often require a large set of hard-to-get low-res/hig…
View article: Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search
Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search Open
Supervised deep learning approaches can artificially increase the resolution of microscopy images by learning a mapping between two image resolutions or modalities. However, such methods often require a large set of hard-to-get low-res/hig…
View article: Exploring self-supervised learning biases for microscopy image representation
Exploring self-supervised learning biases for microscopy image representation Open
Self-supervised representation learning (SSRL) in computer vision relies heavily on simple image transformations such as random rotation, crops, or illumination to learn meaningful and invariant features. Despite acknowledged importance, t…
View article: PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images
PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images Open
For the past few years, deep generative models have increasingly been used in biological research for a variety of tasks. Recently, they have proven to be valuable for uncovering subtle cell phenotypic differences that are not directly dis…
View article: Super-Resolution through StyleGAN Regularized Latent Search: A Realism-Fidelity Trade-off
Super-Resolution through StyleGAN Regularized Latent Search: A Realism-Fidelity Trade-off Open
This paper addresses the problem of super-resolution: constructing a highly resolved (HR) image from a low resolved (LR) one. Recent unsupervised approaches search the latent space of a StyleGAN pre-trained on HR images, for the image that…
View article: ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images
ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images Open
Unlike color photography images, which are consistently encoded into RGB channels, biological images encompass various modalities, where the type of microscopy and the meaning of each channel varies with each experiment. Importantly, the n…
View article: Comprehensive mapping of exon junction complex binding sites reveals universal EJC deposition in Drosophila
Comprehensive mapping of exon junction complex binding sites reveals universal EJC deposition in Drosophila Open
Background The exon junction complex (EJC) is involved in most steps of the mRNA life cycle, ranging from splicing to nonsense-mediated mRNA decay (NMD). It is assembled by the splicing machinery onto mRNA in a sequence-independent manner.…
View article: One Style is All you Need to Generate a Video
One Style is All you Need to Generate a Video Open
In this paper, we propose a style-based conditional video generative model. We introduce a novel temporal generator based on a set of learned sinusoidal bases. Our method learns dynamic representations of various actions that are independe…
View article: Choroid plexuses carry nodal-like cilia that undergo axoneme regression from early adult stage
Choroid plexuses carry nodal-like cilia that undergo axoneme regression from early adult stage Open
Choroid plexuses (ChPs) produce cerebrospinal fluid and sense non-cell-autonomous stimuli to control the homeostasis of the central nervous system. They are mainly composed of epithelial multiciliated cells, whose development and function …
View article: Revealing invisible cell phenotypes with conditional generative modeling
Revealing invisible cell phenotypes with conditional generative modeling Open
Biological sciences, drug discovery and medicine rely heavily on cell phenotype perturbation and microscope observation. However, most cellular phenotypic changes are subtle and thus hidden from us by natural cell variability: two cells in…
View article: Image datasets used in the paper "Revealing invisible cell phenotypes with conditional generative modeling"
Image datasets used in the paper "Revealing invisible cell phenotypes with conditional generative modeling" Open
- BBBC021_selection_128 is a selection of the BBBC021 image dataset from the Broad Bioimage Benchmarck Collection from the Broad Institute - golgi_256_subset is a subset (one plate) of the Golgi Dataset we used (which is about 3 times larg…
View article: Image datasets used in the paper "Revealing invisible cell phenotypes with conditional generative modeling"
Image datasets used in the paper "Revealing invisible cell phenotypes with conditional generative modeling" Open
- BBBC021_selection_128 is a selection of the BBBC021 image dataset from the Broad Bioimage Benchmarck Collection from the Broad Institute - golgi_256_subset is a subset (one plate) of the Golgi Dataset we used (which is about 3 times larg…
View article: No Free Lunch in Self Supervised Representation Learning
No Free Lunch in Self Supervised Representation Learning Open
Self-supervised representation learning in computer vision relies heavily on hand-crafted image transformations to learn meaningful and invariant features. However few extensive explorations of the impact of transformation design have been…
View article: Evolution is not Uniform Along Coding Sequences
Evolution is not Uniform Along Coding Sequences Open
Amino acids evolve at different speeds within protein sequences, because their functional and structural roles are different. Notably, amino acids located at the surface of proteins are known to evolve more rapidly than those in the core. …