Publications

See also my Google Scholar profile and my detailed CV.

2025

• I. Sebag, M. S. Pydi, J.-Y. Franceschi, A. Rakotomamonjy, M. Gartrell, J. Atif, A. Allauzen. “Differentially Private Gradient Flow based on the Sliced Wasserstein Distance”. In: Transactions on Machine Learning Research. 2025.
  • Links:
    • https://openreview.net/forum?id=aiOHc1LGpD;
    • https://arxiv.org/abs/2312.08227;
    • https://hal.science/hal-04664174.
  • Code: https://github.com/ilanasebag/dpswgf.

• A. Schnepf, K. Kassab, J.-Y. Franceschi, L. Caraffa, F. Vasile, J. Mary, A. Comport, V. Gouet-Brunet. “Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder”. In: International Conference on Learning Representations. 2025.
  • Links:
    • https://openreview.net/forum?id=LTDtjrv02Y;
    • https://arxiv.org/abs/2410.22936;
    • https://hal.science/hal-04760484.
  • Project website: https://ig-ae.github.io/.
  • Code:
    • https://github.com/k-kassab/igae;
    • https://github.com/AntoineSchnepf/latent-nerfstudio.
  • Data: https://huggingface.co/datasets/k-kassab/igae-data/tree/main.

• K. Kassab, A. Schnepf, J.-Y. Franceschi, L. Caraffa, J. Mary, V. Gouet-Brunet. “RefinedFields: Radiance Fields Refinement for Planar Scene Representations”. In: Transactions on Machine Learning Research. 2025.
  • Links:
    • https://openreview.net/forum?id=S6JpSsYBDZ;
    • https://arxiv.org/abs/2312.00639;
    • https://hal.science/hal-04318414.
  • Project website: https://refinedfields.github.io/.
  • Code: https://github.com/k-kassab/refinedfields.

• T. Issenhuth, S. Lee, L. Dos Santos, J.-Y. Franceschi, C. Kim, A. Rakotomamonjy. “Improving Consistency Models with Generator-Augmented Flows”. To appear at ICML 2025.
  • Links:
    • https://arxiv.org/abs/2406.09570;
    • https://hal.science/hal-04611719.
  • Code: https://github.com/thibautissenhuth/consistency_GC.

2024

• A. Schnepf, K. Kassab, J.-Y. Franceschi, L. Caraffa, F. Vasile, J. Mary, A. Comport, V. Gouet-Brunet. “Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes”. arXiv:2403.11678. Accepted to the 3DMV CVPR 2024 workshop.
  • Links:
    • https://arxiv.org/abs/2403.11678;
    • https://hal.science/hal-04509207;
    • workshop version.
  • Project website: https://3da-ae.github.io/.

• K. Kassab, A. Schnepf, J.-Y. Franceschi, L. Caraffa, F. Vasile, J. Mary, A. Comport, V. Gouet-Brunet. “Fused-Planes: Improving Planar Representations for Learning Large Sets of 3D Scenes”. arXiv:2410.23742. Preprint.
  • Links:
    • https://arxiv.org/abs/2410.23742;
    • https://hal.science/hal-04761470.
  • Project website: https://fused-planes.github.io/.
  • Code: https://github.com/k-kassab/scaled-ig.

2023

• Y. Yin, M. Kirchmeyer, J.-Y. Franceschi, A. Rakotomamonjy, P. Gallinari. “Continuous PDE Dynamics Forecasting with Implicit Neural Representations”. In: International Conference on Learning Representations. 2023.
  • Links:
    • https://openreview.net/forum?id=B73niNjbPs;
    • https://hal.science/hal-03792179;
    • https://arxiv.org/abs/2209.14855.
  • Video presentation: https://iclr.cc/virtual/2023/poster/12133.
  • Poster: https://hal.science/hal-04081163.
  • Code: https://github.com/mkirchmeyer/DINo.

• J.-Y. Franceschi, M. Gartrell, L. Dos Santos, T. Issenhuth, E. de Bézenac, M. Chen, A. Rakotomamonjy. “Unifying GANs and Score-Based Diffusion as Generative Particle Models”. In: Advances in Neural Information Processing Systems 36. Curran Associates, Inc., 2023, pp. 59729–59760.
  • Links:
    • https://openreview.net/forum?id=HMhEFKDQ6J;
    • https://arxiv.org/abs/2305.16150;
    • https://hal.science/hal-04107806.
  • Project website: https://jyfranceschi.fr/publications/gpm/.
  • Video presentation: https://neurips.cc/virtual/2023/poster/72168.
  • Poster: https://hal.science/hal-04322365. See also the A0 version.
  • Code: https://github.com/White-Link/gpm.

• K. Kassab, A. Schnepf, J.-Y. Franceschi, L. Caraffa, J. Mary, V. Gouet-Brunet. “RefinedFields: Radiance Fields Refinement for Unconstrained Scenes”. arXiv:2312.00639. Preprint.
  • Links:
    • https://arxiv.org/abs/2312.00639;
    • https://hal.science/hal-04318414.
  • Project website: https://refinedfields.github.io/.

2022

• J.-Y. Franceschi, E. de Bézenac, I. Ayed, M. Chen, S. Lamprier, P. Gallinari. “A Neural Tangent Kernel Perspective of GANs”. In: Proceedings of the 39th International Conference on Machine Learning. Vol. 162. Proceedings of Machine Learning Research. Baltimore, MD, USA: PMLR, July 2022, pp. 6660–6704.
  • Links:
    • https://proceedings.mlr.press/v162/franceschi22a.html;
    • https://hal.science/hal-03254591;
    • https://arxiv.org/abs/2106.05566.
  • Video presentations: https://icml.cc/virtual/2022/spotlight/16000.
  • Poster: https://hal.science/hal-03716574.
  • Code: https://github.com/emited/gantk2.

2021

• J. Donà, J.-Y. Franceschi, S. Lamprier, P. Gallinari. “PDE-Driven Spatiotemporal Disentanglement”. In: International Conference on Learning Representations. 2021.
  • Links:
    • https://openreview.net/forum?id=vLaHRtHvfFp;
    • https://hal.science/hal-02911067;
    • https://arxiv.org/abs/2008.01352.
  • Video presentation: https://iclr.cc/virtual/2021/poster/3233.
  • Poster: https://hal.archives-ouvertes.fr/hal-03181039.
  • Code: https://github.com/JeremDona/spatiotemporal_variable_separation.

2020

• J.-Y. Franceschi, E. Delasalles, M. Chen, S. Lamprier, P. Gallinari. “Stochastic Latent Residual Video Prediction”. In: Proceedings of the 37th International Conference on Machine Learning. Vol. 119. Proceedings of Machine Learning Research. Virtual: PMLR, July 2020, pp. 3233–3246.
  • Links:
    • http://proceedings.mlr.press/v119/franceschi20a.html;
    • https://hal.science/hal-02484182;
    • https://arxiv.org/abs/2002.09219.
  • Video presentation: https://icml.cc/virtual/2020/poster/5773.
  • Project website: https://sites.google.com/view/srvp/.
  • Code: https://github.com/edouardelasalles/srvp.
  • Pretrained models: https://data.lip6.fr/srvp/.

2019

• J.-Y. Franceschi, A. Dieuleveut, M. Jaggi. “Unsupervised Scalable Representation Learning for Multivariate Time Series”. In: Advances in Neural Information Processing Systems 32. Curran Associates, Inc., 2019, pp. 4650–4661.
  • Links:
    • https://papers.nips.cc/paper/8713-unsupervised-scalable-representation-learning-for-multivariate-time-series;
    • https://hal.science/hal-01998101;
    • https://arxiv.org/abs/1901.10738.
  • Poster: https://hal.archives-ouvertes.fr/hal-02320167.
  • Code: https://github.com/White-Link/UnsupervisedScalableRepresentationLearningTimeSeries.

2018

• J.-Y. Franceschi, A. Fawzi, O. Fawzi. “Robustness of classifiers to uniform ℓ_p and Gaussian noise”. In: Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (AISTATS). Vol. 84. Proceedings of Machine Learning Research. Playa Blanca, Lanzarote, Canary Islands: PMLR, Apr. 2018, pp. 1280–1288.
  • Links:
    • http://proceedings.mlr.press/v84/franceschi18a.html;
    • https://hal.science/hal-01715012;
    • https://arxiv.org/abs/1802.07971.
  • Poster.

2017

• A.G.M. Ahmed, J. Guo, D.M. Yan, J.-Y. Franceschi, X. Zhang, O. Deussen. “A Simple Push-Pull Algorithm for Blue-Noise Sampling”. In: IEEE Transactions on Visualization and Computer Graphics 23.12 (Dec. 2017), pp. 2496–2508.
  • Link: https://doi.org/10.1109/TVCG.2016.2641963