Michal Drozdzal

Computer Science · Physical Sciences

20h-index7.7kcitations80works1.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(14), Generative Adversarial Networks and Image Synthesis(12), Gastrointestinal Bleeding Diagnosis and Treatment(12), Advanced Image and Video Retrieval Techniques(9), Image Retrieval and Classification Techniques(9)

Publications80 total

The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models
ArXiv.org·2025Open Access
Increasing the Utility of Synthetic Images through Chamfer Guidance
arXiv (Cornell University)·2025Open Access
Multi-Modal Language Models as Text-to-Image Model Evaluators
arXiv (Cornell University)·2025Open Access
Object-centric Binding in Contrastive Language-Image Pretraining
arXiv (Cornell University)·2025Open Access
EvalGIM: A Library for Evaluating Generative Image Models
arXiv (Cornell University)·2024Open Access
Improving Geo-Diversity of Generated Images with Contextualized Vendi Score Guidance
Lecture notes in computer science·2024
Boosting Latent Diffusion with Perceptual Objectives
arXiv (Cornell University)·2024Open Access
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
arXiv (Cornell University)·2024· 2 citedOpen Access
Consistency-diversity-realism Pareto fronts of conditional image generative models
arXiv (Cornell University)·2024· 3 citedOpen Access
Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
arXiv (Cornell University)·2024Open Access
Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
2024· 3 citedOpen Access
Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Improving Text-to-Image Consistency via Automatic Prompt Optimization
arXiv (Cornell University)·2024· 6 citedOpen Access
InCoRo: In-Context Learning for Robotics Control with Feedback Loops
arXiv (Cornell University)·2024· 2 citedOpen Access
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
2024Open Access
Feedback-guided Data Synthesis for Imbalanced Classification
arXiv (Cornell University)·2023· 2 citedOpen Access
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
arXiv (Cornell University)·2023· 1 citedOpen Access
Improved baselines for vision-language pre-training
arXiv (Cornell University)·2023· 3 citedOpen Access
Controllable Image Generation via Collage Representations
arXiv (Cornell University)·2023· 1 citedOpen Access
Instance-Conditioned GAN Data Augmentation for Representation Learning
arXiv (Cornell University)·2023Open Access
page 1 of 4Next →

Frequent Co-authors

Adriana Romero(21), Petia Radeva(13), Carolina Malagelada(13), Fernando Azpiroz(13), Jordi Vitrià(13), Santi Seguí(12), Yoshua Bengio(8), Gabriel Chartrand(7), Eugene Vorontsov(7), Adriana Romero-Soriano(6), Samuel Kadoury(5), Matthew J. Muckley(5), Simon Jégou(4), David Vázquez(4), Chris Pal(4), An Tang(3), Xavier Giró-i-Nieto(3), Aaron Courville(3), Zizhao Zhang(3), Pascal Vincent(3)