AR
Adriana Romero
cs.CVcs.AIcs.LGcs.CLstat.MLcs.CYcs.HCcs.ROeess.IVColonoscopy
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
Preprints & journals
73 papers in the corpus · 2014–2026FeaTok: 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
Loose Lips: Understanding Privacy Leakage in Agentic Dialogue2610.14071v1 · Soumya Sharma, Ayana Hussain, Heber Hwang Arcolezi 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
Grounding Computer Use Agents on Human Demonstrations2511.07332v2 · Aarash Feizi, Shravan Nayak, Xiangru Jian et al.2025 · 1 citationarXiv
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
DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models2506.05108v1 · Revant Teotia, Candace Ross, Karen Ullrich 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
PairBench: Are Vision-Language Models Reliable at Comparing What They See?2502.15210v3 · Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano et al.2025 · 0 citationsarXiv
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
Augmented Conditioning Is Enough For Effective Training Image Generation2502.04475v1 · Jiahui Chen, Amy Zhang, Adriana Romero-Soriano2025 · 0 citationsarXiv
What makes a good metric? Evaluating automatic metrics for text-to-image consistency2412.13989v1 · Candace Ross, Melissa Hall, Adriana Romero Soriano et al.2024 · 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
FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation2410.17358v1 · Rohan Sukumaran, Aarash Feizi, Adriana Romero-Sorian et al.2024 · 0 citationsarXiv
Decomposed evaluations of geographic disparities in text-to-image models2406.11988v1 · Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa et al.2024 · 1 citationarXiv
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
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning2403.14421v3 · Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi et al.2024 · 0 citationsarXiv
GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning2401.01990v2 · Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano et al.2024 · 1 citationarXiv
A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions2312.08578v2 · Jack Urbanek, Florian Bordes, Pietro Astolfi et al.2023 · 24 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
Graph Inductive Biases in Transformers without Message Passing2305.17589v1 · Liheng Ma, Chen Lin, Derek Lim et al.2023 · 21 citationsPMLR 202 (2023) 23321-23337
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
On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects2301.00512v1 · Sumana Basu, Marc-Andr'e Legault, Adriana Romero-Soriano et al.2023 · 4 citationsarXiv
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction2210.00978v1 · Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai et al.2022 · 6 citationsarXiv
Revisiting Hotels-50K and Hotel-ID2207.10200v1 · Aarash Feizi, Arantxa Casanova, Adriana Romero-Soriano et al.2022 · 0 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
Fairness Indicators for Systematic Assessments of Visual Feature Extractors2202.07603v1 · Priya Goyal, Adriana Romero Soriano, Caner Hazirbas et al.2022 · 17 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
Graph Attention Networks with Positional Embeddings2105.04037v3 · Liheng Ma, Reihaneh Rabbany, Adriana Romero-Soriano2021 · 23 citationsarXiv
Generating unseen complex scenes: are we there yet?2012.04027v1 · Arantxa Casanova, Michal Drozdzal, Adriana Romero-Soriano2020 · 13 citationsarXiv
Career total: 101 works. 73 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.