MD
Michal Drozdzal
cs.CVcs.AIcs.LGstat.MLcs.CLcs.ROeess.IVcs.HCAlgorithmsDeep learning
On Valency
published · living versionsW_5352xgra·v1 · currentpublished
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
with Jure Zbontar, Florian Knoll, Anuroop Sriram, Tullie Murrell +22
1 version
W_gkgwmbms·v1published
Preprints & journals
66 papers in the corpus · 2011–2026FeaTok: Feature-Loss Tokenization for Image Generation2610.22060v1 · Zhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez et al.2026 · 0 citationsarXiv
ESC: Escaping 2D Diffusion Ambiguity with Geometric Constraints for Consistent Novel View Synthesis2610.23732v1 · Ge Ya Luo, Daniel Severo, Brian Karrer et al.2026 · 0 citationsarXiv
RoboJEPA: Scaling Robotic Latent World Models2610.10515v1 · Artem Zholus, Nicolas Beltran-Velez, Jianhao Yuan et al.2026 · 0 citationsarXiv
World Action Modeling with Progressive Visual Planning2610.02508v1 · Fei Zhang, Zhaochong An, Duncan Frost et al.2026 · 0 citationsarXiv
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL2606.19162v1 · Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng et al.2026 · 0 citationsarXiv
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs2605.23883v1 · Rim Assouel, Amir Bar, Michal Drozdzal et al.2026 · 0 citationsarXiv
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation2602.17200v2 · Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer et al.2026 · 0 citationsarXiv
Inference-time Physics Alignment of Video Generative Models with Latent World Models2601.10553v2 · Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich et al.2026 · 1 citationarXiv
Unified Text-Image Generation with Weakness-Targeted Post-Training2601.04339v3 · Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han et al.2026 · 0 citationsarXiv
TV2TV: A Unified Framework for Interleaved Language and Video Generation2512.05103v2 · Xiaochuang Han, Youssef Emad, Melissa Hall et al.2025 · 0 citationsarXiv
The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models2510.19557v2 · Zhang Xiaofeng, Aaron Courville, Michal Drozdzal et al.2025 · 0 citationsarXiv
Improving the Physics of Video Generation with VJEPA-2 Reward Signal2510.21840v1 · Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich et al.2025 · 0 citationsWinning entry of the ICCV 2025 Physics IQ Challenge
Controlling Multimodal LLMs via Reward-guided Decoding2508.11616v1 · Oscar Manas, Pierluca D'Oro, Koustuv Sinha et al.2025 · 0 citationsarXiv
Increasing the Utility of Synthetic Images through Chamfer Guidance2508.10631v2 · Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat et al.2025 · 1 citationarXiv
Multimodal Language Models as Text-to-Image Model Evaluators2505.00759v3 · Jiahui Chen, Candace Ross, Reyhane Askari-Hemmat et al.2025 · 0 citationsarXiv
Entropy Rectifying Guidance for Diffusion and Flow Models2504.13987v2 · Tariq Berrada Ifriqi, Adriana Romero-Soriano, Michal Drozdzal et al.2025 · 1 citationarXiv
Improving the Scaling Laws of Synthetic Data with Deliberate Practice2502.15588v1 · Reyhane Askari-Hemmat, Mohammad Pezeshki, Elvis Dohmatob et al.2025 · 0 citationsarXiv
Object-centric Binding in Contrastive Language-Image Pretraining2502.14113v1 · Rim Assouel, Pietro Astolfi, Florian Bordes et al.2025 · 0 citationsarXiv
EvalGIM: A Library for Evaluating Generative Image Models2412.10604v2 · Melissa Hall, Oscar Manas, Reyhane Askari-Hemmat et al.2024 · 0 citationsarXiv
Boosting Latent Diffusion with Perceptual Objectives2411.04873v2 · Tariq Berrada, Pietro Astolfi, Melissa Hall et al.2024 · 0 citationsarXiv
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models2411.03177v2 · Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall et al.2024 · 1 citationarXiv
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control2409.08861v5 · Carles Domingo-Enrich, Michal Drozdzal, Brian Karrer et al.2024 · 3 citationsarXiv
Consistency-diversity-realism Pareto fronts of conditional image generative models2406.10429v1 · Pietro Astolfi, Marlene Careil, Melissa Hall et al.2024 · 3 citationsarXiv
Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance2406.04551v2 · Reyhane Askari Hemmat, Melissa Hall, Alicia Sun et al.2024 · 2 citationsarXiv
Towards Geographic Inclusion in the Evaluation of Text-to-Image Models2405.04457v1 · Melissa Hall, Samuel J. Bell, Candace Ross et al.2024 · 10 citationsarXiv
Improving Text-to-Image Consistency via Automatic Prompt Optimization2403.17804v1 · Oscar Manas, Pietro Astolfi, Melissa Hall et al.2024 · 7 citationsarXiv
InCoRo: In-Context Learning for Robotics Control with Feedback Loops2402.05188v1 · Jiaqiang Ye Zhu, Carla Gomez Cano, David Vazquez Bermudez et al.2024 · 3 citationsarXiv
Feedback-guided Data Synthesis for Imbalanced Classification2310.00158v2 · Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes et al.2023 · 2 citationsarXiv
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity2308.06198v3 · Melissa Hall, Candace Ross, Adina Williams et al.2023 · 1 citationarXiv
Improved baselines for vision-language pre-training2305.08675v2 · Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano et al.2023 · 4 citationsTransactions on Machine Learning Research, 10/2023, issn 2835-8856
Controllable Image Generation via Collage Representations2304.13722v1 · Arantxa Casanova, Marlene Careil, Adriana Romero-Soriano et al.2023 · 2 citationsarXiv
Instance-Conditioned GAN Data Augmentation for Representation Learning2303.09677v1 · Pietro Astolfi, Arantxa Casanova, Jakob Verbeek et al.2023 · 1 citationarXiv
Learning to Substitute Ingredients in Recipes2302.07960v1 · Bahare Fatemi, Quentin Duval, Rohit Girdhar et al.2023 · 4 citationsarXiv
The Liver Tumor Segmentation Benchmark (LiTS).36481607 · Bilic, Patrick, Christ, Patrick, Li, Hongwei Bran et al.2023 · 1,394 citationsMedical image analysis. 2023;84:102680
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations2211.01866v1 · Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero et al.2022 · 12 citationsarXiv
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction2210.00978v1 · Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai et al.2022 · 6 citationsarXiv
On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction2203.16392v1 · Tim Bakker, Matthew Muckley, Adriana Romero-Soriano et al.2022 · 6 citationsarXiv
Parameter Prediction for Unseen Deep Architectures2110.13100v1 · Boris Knyazev, Michal Drozdzal, Graham W. Taylor et al.2021 · 19 citationsarXiv
Instance-Conditioned GAN2109.05070v2 · Arantxa Casanova, Marlene Careil, Jakob Verbeek et al.2021 · 62 citationsarXiv
Active 3D Shape Reconstruction from Vision and Touch2107.09584v2 · Edward J. Smith, David Meger, Luis Pineda et al.2021 · 10 citationsPublished at Neurips 2021
Generating unseen complex scenes: are we there yet?2012.04027v1 · Arantxa Casanova, Michal Drozdzal, Adriana Romero-Soriano2020 · 13 citationsarXiv
Instance Selection for GANs2007.15255v2 · Terrance DeVries, Michal Drozdzal, Graham W. Taylor2020 · 22 citationsarXiv
Active MR k-space Sampling with Reinforcement Learning2007.10469v2 · Luis Pineda, Sumana Basu, Adriana Romero et al.2020 · 58 citationsLNCS vol. 12262 (2020) 23-33
3D Shape Reconstruction from Vision and Touch2007.03778v2 · Edward J. Smith, Roberto Calandra, Adriana Romero et al.2020 · 28 citationsarXiv
Extending Unsupervised Neural Image Compression With Supervised Multitask Learning2004.07041v1 · David Tellez, Diederik Hoppener, Cornelis Verhoef et al.2020 · 33 citationsarXiv
Needles in Haystacks: On Classifying Tiny Objects in Large Images1908.06037v2 · Nick Pawlowski, Suvrat Bhooshan, Nicolas Ballas et al.2019 · 12 citationsarXiv
On the Evaluation of Conditional GANs1907.08175v3 · Terrance DeVries, Adriana Romero, Luis Pineda et al.2019 · 27 citationsarXiv
Elucidating image-to-set prediction: An analysis of models, losses and datasets1904.05709v2 · Luis Pineda, Amaia Salvador, Michal Drozdzal et al.2019 · 6 citationsarXiv
Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition1902.03051v1 · Zizhao Zhang, Adriana Romero, Matthew J. Muckley et al.2019 · 106 citationsarXiv
Inverse Cooking: Recipe Generation from Food Images1812.06164v2 · Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto et al.2018 · 176 citationsarXiv
Career total: 87 works. 66 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.