publications

Work on generative models, neural representations, and efficient adaptation.

2026

  1. TensLoRA: Tensor Alternatives for Low-Rank Adaptation
    Axel Marmoret, Reda Bensaid, Jonathan Lys, and 2 more authors
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026
  2. Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decoding
    Aymen Sarhane, Fouad Lbakali, Mouad Souissi, and 2 more authors
    In IEEE World Congress on Computational Intelligence (WCCI), 2026
  3. Key Ingredients for EEG Foundation Models: What Works - and What Doesn’t
    Giulia Lioi, Yassine El Ouahidi, Jonathan Lys, and 5 more authors
    In European Signal Processing Conference (EUSIPCO), 2026
  4. How Transferable Are EEG Foundation Models? A Case Study on Sleep Staging
    Alix Lamouroux, Lucas Benoit, Jonathan Lys, and 2 more authors
    In European Signal Processing Conference (EUSIPCO), 2026
  5. Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training
    Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, and 4 more authors
    In European Signal Processing Conference (EUSIPCO), 2026
  6. Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers
    Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, and 4 more authors
    In European Signal Processing Conference (EUSIPCO), 2026
  7. D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
    Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, and 4 more authors
    arXiv preprint arXiv:2603.19146, 2026

2025

  1. REVE: A Foundation Model for EEG – Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
    Yassine El Ouahidi, Jonathan Lys, Philipp Thölke, and 5 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2025

2024

  1. FICUS: Few-shot Image Classification with Unsupervised Segmentation
    Jonathan Lys, Frédéric Lin, Clément Béliveau, and 4 more authors
    In European Signal Processing Conference (EUSIPCO), 2024