Selected Papers
Google Scholar ↗ | All my research papers ↓
- 2026 Best Paper
FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion
MUCG Workshop at ECCV 2026
Hugo Caselles-Dupré, Mathis Koroglu, Guillaume Jeanneret, Arnaud Dapogny, Matthieu Cord
- 2026 Oral
JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation
AI4VA Workshop at ECCV 2026
Mathis Koroglu, Guillaume Jeanneret, Hugo Caselles-Dupré, Matthieu Cord, Arnaud Dapogny
- 2024
Mind-to-Image: Projecting Visual Mental Imagination of the Brain from fMRI
ICML 2024 Workshop on AI4Science
Hugo Caselles-Dupré, Charles Mellerio, Paul Hérent, Alizée Lopez-Persem, Benoit Béranger, Mathieu Soularue, Pierre Fautrel, Gauthier Vernier, Matthieu Cord
- 2022
Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
NeurIPS 2022
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
- 2019
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
NeurIPS 2019
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2018
Word2Vec applied to Recommendation: Hyperparameters Matter
ACM RecSys 2018
H. Caselles-Dupré, F. Lesaint, J. Royo-Letelier
All my research papers
28 publications, ordered by year. Google Scholar ↗
- 2026 Best Paper
FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion
MUCG Workshop at ECCV 2026
Hugo Caselles-Dupré, Mathis Koroglu, Guillaume Jeanneret, Arnaud Dapogny, Matthieu Cord
- 2026
HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane
arXiv preprint
Hugo Caselles-Dupré
- 2026 Oral
JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation
AI4VA Workshop at ECCV 2026
Mathis Koroglu, Guillaume Jeanneret, Hugo Caselles-Dupré, Matthieu Cord, Arnaud Dapogny
- 2026
Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization
MUCG Workshop at ECCV 2026
Guillaume Jeanneret, Mathis Koroglu, Hugo Caselles-Dupré, Arnaud Dapogny, Matthieu Cord
- 2025
OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models
CVEU Workshop at CVPR 2025
Mathis Koroglu, Hugo Caselles-Dupré, Guillaume Jeanneret Sanmiguel, Matthieu Cord
- 2025
Proportion and Perspective Control for Flow-Based Image Generation
arXiv preprint
Julien Boudier, Hugo Caselles-Dupré
- 2025
Weaving the Future: Generative AI and the Reimagining of Fashion Design
Tisser le futur : L'IA g{é}n{é}rative et le design de mode, Sorbonne Universit{é}, Jan 2025, Paris, France
Pierre-Marie Chauvin, Angèle Merlin, Xavier Fresquet, Hugo Caselles-Dupré, Benjamin Simmenauer, Mathieu de Fayet
- 2024
Mind-to-Image: Projecting Visual Mental Imagination of the Brain from fMRI
ICML 2024 Workshop on AI4Science
Hugo Caselles-Dupré, Charles Mellerio, Paul Hérent, Alizée Lopez-Persem, Benoit Béranger, Mathieu Soularue, Pierre Fautrel, Gauthier Vernier, Matthieu Cord
- 2023
Enhancing Agent Communication and Learning through Action and Language
IMOL 2023 Workshop
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
- 2023
Help Me Explore: Combining Autotelic and Social Learning via Active Goal Queries
OpenReview, 2023
Ahmed Akakzia, Hugo Caselles-Dupré, Olivier Serris, Mohamed Chetouani, Olivier Sigaud, Cédric Colas
- 2023
Toward Teachable Autotelic Agents
IEEE Transactions on Cognitive and Developmental Systems 15(3), 1070-1084
Olivier Sigaud, Ahmed Akakzia, Hugo Caselles-Dupré, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani
- 2023
Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind
arXiv preprint
Clémence Grislain, Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
- 2022
Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
NeurIPS 2022 Workshop
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
- 2022
Pedagogical Demonstrations and Pragmatic Learning in Artificial Tutor-Learner Interactions
HIRL Workshop at HRI 2022
Hugo Caselles-Dupré, Mohamed Chetouani, Olivier Sigaud
- 2022
Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
NeurIPS 2022
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
- 2021
Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?
arXiv preprint
Hugo Caselles-Dupré, Michaël Garcia-Ortiz, David Filliat
- 2021
On the Sensory Commutativity of Action Sequences for Embodied Agents
AAMAS 2021 - 20th International Conference on Autonomous Agents and Multiagent Systems
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2021
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
International Joint Conference on Neural Networks (IJCNN) 2021, July, Online
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2020
Electric Dreams of Ukiyo: A Series of Japanese Artworks Created by an Artificial Intelligence
Patterns 1(2), 100026
Gauthier Vernier, Hugo Caselles-Dupré, Pierre Fautrel
- 2020
Facets of AGI: Where Science Meets Spirituality
Patterns 1(8), 100149
Gauthier Vernier, Hugo Caselles-Dupré, Pierre Fautrel
- 2020
Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
NeurIPS 2020 Workshop on BabyMind
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2019
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
Workshop on Multi-Task and Lifelong Reinforcement Learning, ICML 2019, June 9-15, Long Beach, USA
R. Traoré*, H. Caselles-Dupré*, T. Lesort*, T. Sun, N. Díaz-Rodríguez, D. Filliat
- 2019
DisCoRL: Continual Reinforcement Learning via Policy Distillation
arXiv preprint
René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Guanghang Cai, Natalia Díaz-Rodríguez, David Filliat
- 2019
Generative Models from the perspective of Continual Learning
International Joint Conference on Neural Networks (IJCNN) 2019, July 14-19, Budapest, Hungary
T. Lesort*, H. Caselles-Dupré*, M. Garcia-Ortiz, J-F. Goudou, D. Filliat
- 2019
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
NeurIPS 2019
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2018
Continual State Representation Learning for Reinforcement Learning using Generative Replay
Workshop on Continual Learning, NeurIPS 2018, December 2-9, Montréal, Canada
H. Caselles-Dupré, M. Garcia-Ortiz, D. Filliat
- 2018
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
Workshop on Continual Unsupervised Sensorimotor Learning, ICDL-EpiRob 2018, September 16-20, Tokyo, Japan
H. Caselles-Dupré, L. Annabi, O. Hagen, M. Garcia-Ortiz, D. Filliat
- 2018
Word2Vec applied to Recommendation: Hyperparameters Matter
ACM RecSys 2018
H. Caselles-Dupré, F. Lesaint, J. Royo-Letelier
