Adriana Romero-Soriano

64 papers A* 10Journal 48Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Bootstrapping Personalized Insulin Therapy via Model-Based Reinforcement Learning: An In Silico Study. AAAI Sumana Basu, Flemming Kondrup, Adriana Romero-Soriano, Doina Precup
2026	J	`jnl`	GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation. CoRR Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer, Adriana Romero-Soriano, Michal Drozdzal, Olga Russakovsky
2026	J	`jnl`	Inference-time Physics Alignment of Video Generative Models with Latent World Models. CoRR Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano
2025	J	`jnl`	Augmented Conditioning Is Enough For Effective Training Image Generation. CoRR Jiahui Chen, Amy Zhang, Adriana Romero-Soriano
2025	A*	`conf`	Boosting Latent Diffusion with Perceptual Objectives. ICLR Tariq Berrada, Pietro Astolfi, Melissa Hall, Marton Havasi, Yohann Benchetrit, Adriana Romero-Soriano, Karteek Alahari, Michal Drozdzal, Jakob Verbeek
2025	J	`jnl`	Controlling Multimodal LLMs via Reward-guided Decoding. CoRR Oscar Mañas, Pierluca D'Oro, Koustuv Sinha, Adriana Romero-Soriano, Michal Drozdzal, Aishwarya Agrawal
2025	J	`jnl`	DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models. CoRR Revant Teotia, Candace Ross, Karen Ullrich, Sumit Chopra, Adriana Romero-Soriano, Melissa Hall, Matthew J. Muckley
2025	J	`jnl`	Entropy Rectifying Guidance for Diffusion and Flow Models. CoRR Tariq Berrada Ifriqi, Adriana Romero-Soriano, Michal Drozdzal, Jakob Verbeek, Karteek Alahari
2025	J	`jnl`	Grounding Computer Use Agents on Human Demonstrations. CoRR Aarash Feizi, Shravan Nayak, Xiangru Jian, Kevin Qinghong Lin, Kaixin Li, Rabiul Awal, Xing Han Lù, Johan Obando-Ceron, Juan A. Rodríguez, Nicolas Chapados, David Vázquez, Adriana Romero-Soriano, Reihaneh Rabbany, Perouz Taslakian, Christopher Pal, Spandana Gella, Sai Rajeswar
2025	J	`jnl`	Improving the Physics of Video Generation with VJEPA-2 Reward Signal. CoRR Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano
2025	A*	`conf`	Improving the Scaling Laws of Synthetic Data with Deliberate Practice. ICML Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2025	J	`jnl`	Improving the Scaling Laws of Synthetic Data with Deliberate Practice. CoRR Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2025	J	`jnl`	Increasing the Utility of Synthetic Images through Chamfer Guidance. CoRR Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat, Melissa Hall, Jakob Verbeek, Adriana Romero-Soriano, Michal Drozdzal
2025	J	`jnl`	Multi-Modal Language Models as Text-to-Image Model Evaluators. CoRR Jiahui Chen, Candace Ross, Reyhane Askari Hemmat, Koustuv Sinha, Melissa Hall, Michal Drozdzal, Adriana Romero-Soriano
2025	J	`jnl`	Object-centric Binding in Contrastive Language-Image Pretraining. CoRR Rim Assouel, Pietro Astolfi, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano
2025	J	`jnl`	PairBench: A Systematic Framework for Selecting Reliable Judge VLMs. CoRR Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano, Reihaneh Rabbany, Spandana Gella, Valentina Zantedeschi, João Monteiro
2025	J	`jnl`	The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models. CoRR Xiaofeng Zhang, Aaron C. Courville, Michal Drozdzal, Adriana Romero-Soriano
2024	A*	`conf`	A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions. CVPR Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson, Vasu Sharma, Adriana Romero-Soriano
2024	J	`jnl`	Boosting Latent Diffusion with Perceptual Objectives. CoRR Tariq Berrada, Pietro Astolfi, Jakob Verbeek, Melissa Hall, Marton Havasi, Michal Drozdzal, Yohann Benchetrit, Adriana Romero-Soriano, Karteek Alahari
2024	J	`jnl`	Consistency-diversity-realism Pareto fronts of conditional image generative models. CoRR Pietro Astolfi, Marlène Careil, Melissa Hall, Oscar Mañas, Matthew J. Muckley, Jakob Verbeek, Adriana Romero-Soriano, Michal Drozdzal
2024	J	`jnl`	DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity. Trans. Mach. Learn. Res. Melissa Hall, Candace Ross, Adina Williams, Nicolas Carion, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning. CoRR Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero-Soriano, Kamalika Chaudhuri, Mike Rabbat, Chuan Guo
2024	J	`jnl`	Decomposed evaluations of geographic disparities in text-to-image models. CoRR Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa, Oindrila Saha, Adina Williams, Adriana Romero-Soriano, Megan Richards, Polina Kirichenko, Melissa Hall
2024	J	`jnl`	EvalGIM: A Library for Evaluating Generative Image Models. CoRR Melissa Hall, Oscar Mañas, Reyhane Askari Hemmat, Mark Ibrahim, Candace Ross, Pietro Astolfi, Tariq Berrada Ifriqi, Marton Havasi, Yohann Benchetrit, Karen Ullrich, Carolina Braga, Abhishek Charnalia, Maeve Ryan, Mike Rabbat, Michal Drozdzal, Jakob Verbeek, Adriana Romero-Soriano
2024	J	`jnl`	FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation. CoRR Rohan Sukumaran, Aarash Feizi, Adriana Romero-Soriano, Golnoosh Farnadi
2024	J	`jnl`	Feedback-guided Data Synthesis for Imbalanced Classification. Trans. Mach. Learn. Res. Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning. CoRR Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano, Reihaneh Rabbany
2024	—	`conf`	Improving Geo-Diversity of Generated Images with Contextualized Vendi Score Guidance. ECCV (87) Reyhane Askari Hemmat, Melissa Hall, Alicia Sun, Candace Ross, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance. CoRR Reyhane Askari Hemmat, Melissa Hall, Alicia Sun, Candace Ross, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	Improving Text-to-Image Consistency via Automatic Prompt Optimization. CoRR Oscar Mañas, Pietro Astolfi, Melissa Hall, Candace Ross, Jack Urbanek, Adina Williams, Aishwarya Agrawal, Adriana Romero-Soriano, Michal Drozdzal
2024	J	`jnl`	Improving Text-to-Image Consistency via Automatic Prompt Optimization. Trans. Mach. Learn. Res. Oscar Mañas, Pietro Astolfi, Melissa Hall, Candace Ross, Jack Urbanek, Adina Williams, Aishwarya Agrawal, Adriana Romero-Soriano, Michal Drozdzal
2024	J	`jnl`	On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models. CoRR Tariq Berrada, Pietro Astolfi, Melissa Hall, Reyhane Askari Hemmat, Yohann Benchetrit, Marton Havasi, Matthew J. Muckley, Karteek Alahari, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
2024	A*	`conf`	On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models. NeurIPS Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall, Reyhane Askari Hemmat, Yohann Benchetrit, Marton Havasi, Matthew J. Muckley, Karteek Alahari, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
2024	—	`conf`	Towards Geographic Inclusion in the Evaluation of Text-to-Image Models. FAccT Melissa Hall, Samuel J. Bell, Candace Ross, Adina Williams, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	Towards Geographic Inclusion in the Evaluation of Text-to-Image Models. CoRR Melissa Hall, Samuel J. Bell, Candace Ross, Adina Williams, Michal Drozdzal, Adriana Romero-Soriano
2024	J	`jnl`	What makes a good metric? Evaluating automatic metrics for text-to-image consistency. CoRR Candace Ross, Melissa Hall, Adriana Romero-Soriano, Adina Williams
2023	J	`jnl`	A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions. CoRR Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson, Vasu Sharma, Adriana Romero-Soriano
2023	J	`jnl`	Controllable Image Generation via Collage Representations. CoRR Arantxa Casanova, Marlène Careil, Adriana Romero-Soriano, Christopher J. Pal, Jakob Verbeek, Michal Drozdzal
2023	J	`jnl`	DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity. CoRR Melissa Hall, Candace Ross, Adina Williams, Nicolas Carion, Michal Drozdzal, Adriana Romero-Soriano
2023	J	`jnl`	Feedback-guided Data Synthesis for Imbalanced Classification. CoRR Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano
2023	A*	`conf`	Graph Inductive Biases in Transformers without Message Passing. ICML Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim
2023	J	`jnl`	Graph Inductive Biases in Transformers without Message Passing. CoRR Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim
2023	J	`jnl`	Improved baselines for vision-language pre-training. CoRR Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
2023	J	`jnl`	Improved baselines for vision-language pre-training. Trans. Mach. Learn. Res. Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
2023	J	`jnl`	Instance-Conditioned GAN Data Augmentation for Representation Learning. CoRR Pietro Astolfi, Arantxa Casanova, Jakob Verbeek, Pascal Vincent, Adriana Romero-Soriano, Michal Drozdzal
2023	J	`jnl`	Learning to Substitute Ingredients in Recipes. CoRR Bahare Fatemi, Quentin Duval, Rohit Girdhar, Michal Drozdzal, Adriana Romero-Soriano
2023	A*	`conf`	On the Challenges of Using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects. AAAI Sumana Basu, Marc-André Legault, Adriana Romero-Soriano, Doina Precup
2023	J	`jnl`	On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects. CoRR Sumana Basu, Marc-André Legault, Adriana Romero-Soriano, Doina Precup
2022	—	`conf`	Fairness Indicators for Systematic Assessments of Visual Feature Extractors. FAccT Priya Goyal, Adriana Romero-Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier
2022	J	`jnl`	Fairness Indicators for Systematic Assessments of Visual Feature Extractors. CoRR Priya Goyal, Adriana Romero-Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier
2022	—	`conf`	On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction. MIDL Tim Bakker, Matthew J. Muckley, Adriana Romero-Soriano, Michal Drozdzal, Luis Pineda
2022	J	`jnl`	On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction. CoRR Tim Bakker, Matthew J. Muckley, Adriana Romero-Soriano, Michal Drozdzal, Luis Pineda
2022	J	`jnl`	Revisiting Hotels-50K and Hotel-ID. CoRR Aarash Feizi, Arantxa Casanova, Adriana Romero-Soriano, Reihaneh Rabbany
2022	J	`jnl`	Uncertainty-Driven Active Vision for Implicit Scene Reconstruction. CoRR Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai, David Meger, Adriana Romero-Soriano
2021	A*	`conf`	Active 3D Shape Reconstruction from Vision and Touch. NeurIPS Edward J. Smith, David Meger, Luis Pineda, Roberto Calandra, Jitendra Malik, Adriana Romero-Soriano, Michal Drozdzal
2021	—	`conf`	Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics. NeurIPS Datasets and Benchmarks Charan Reddy, Deepak Sharma, Soroush Mehri, Adriana Romero-Soriano, Samira Shabanian, Sina Honari
2021	—	`conf`	Graph Attention Networks with Positional Embeddings. PAKDD (1) Liheng Ma, Reihaneh Rabbany, Adriana Romero-Soriano
2021	J	`jnl`	Graph Attention Networks with Positional Embeddings. CoRR Liheng Ma, Reihaneh Rabbany, Adriana Romero-Soriano
2021	A*	`conf`	Instance-Conditioned GAN. NeurIPS Arantxa Casanova, Marlène Careil, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2021	J	`jnl`	Instance-Conditioned GAN. CoRR Arantxa Casanova, Marlène Careil, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2021	A*	`conf`	Parameter Prediction for Unseen Deep Architectures. NeurIPS Boris Knyazev, Michal Drozdzal, Graham W. Taylor, Adriana Romero-Soriano
2021	J	`jnl`	Parameter Prediction for Unseen Deep Architectures. CoRR Boris Knyazev, Michal Drozdzal, Graham W. Taylor, Adriana Romero-Soriano
2020	J	`jnl`	Generating unseen complex scenes: are we there yet? CoRR Arantxa Casanova, Michal Drozdzal, Adriana Romero-Soriano
2016	J	`jnl`	Processing of Extremely High-Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest-Part A: 2-D Contest. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. Manuel Campos-Taberner, Adriana Romero-Soriano, Carlo Gatta, Gustau Camps-Valls, Adrien Lagrange, Bertrand Le Saux, Anne Beaupère, Alexandre Boulch, Adrien Chan-Hon-Tong, Stéphane Herbin, Hicham Randrianarivo, Marin Ferecatu, Michal Shimoni, Gabriele Moser, Devis Tuia