Skip to content
Cheick T. Cissé

Research

Research

8 peer-reviewed papers and one patent, across generative modelling for language, vision and wireless systems. Each entry below says plainly what the work found.

Peer review

Programme committee reviewer for:

  • 2027AAAI 2027Reviewer
  • 2026NeurIPS 2026Reviewer

Qualifications

  • CNU qualification, sections 27 & 61

    Nationally qualified for Associate Professor positions in Computer Science and Signal Processing.

  • Patent (filed)

    Method for incorporating propagation-model error into indoor Wi-Fi optimisation.

Publications

International conferences

2026
Findings of ACL 2026Sole author+3–4 BLEU

Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation

Cheick Tidiani Cissé

Findings of the Association for Computational Linguistics: ACL 2026, pp. 24433–24446

Built and released a 67k quality-scored French↔Bambara corpus, showing that filtering for quality beats scaling raw volume in extremely low-resource translation. +3–4 BLEU over baselines, confirmed by human evaluation.

2025
ICASSP 2025Top-5 / 16+ teams

Generalizable Indoor Path Loss Prediction

C. T. Cissé, et al.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025 — Grand Challenge track

A ResUNet with physics-informed inputs that predicts indoor radio maps for buildings and frequencies it has never seen. Top-5 of 16+ teams in the ICASSP 2025 Grand Challenge.

2024
EuCAP 2024

Fine Tuning an AI-based Indoor Radio Propagation Model with Crowd-sourced Data

C. T. Cissé, O. Baala, V. Guillet, F. Spies, A. Caminada

18th European Conference on Antennas and Propagation (EuCAP) 2024

Closing the simulation-to-reality gap: adapting a model trained on simulated data to noisy real-world 5 GHz Wi-Fi measurements from live home networks.

2023
IFIP Networking 20232.5 dB RMSE

IRGAN: cGAN-based Indoor Radio Map Prediction

C. T. Cissé, O. Baala, V. Guillet, F. Spies, A. Caminada

IFIP Networking Conference 2023

Predicts a full indoor Wi-Fi coverage map from a single 2D floor-plan image, replacing ray-tracing simulations that take orders of magnitude longer.

2022
ICASSP 2022

A New Deep Learning Method for Multispectral Image Time Series Completion Using Hyperspectral Data

C. T. Cissé, A. Alboody, M. Puigt, G. Roussel, V. Vantrepotte, C. Jamet, T. K. Tran

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022

Fuses Sentinel-2 and Sentinel-3 imagery to reconstruct missing dates in satellite time series, raising effective temporal resolution for coastal water monitoring.

National symposia

2024
ROADEF 2024

Planification radio automatique en intérieur

C. T. Cissé, O. Baala, V. Guillet, F. Spies, A. Caminada

25e congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision

Combinatorial optimisation for automatic access-point placement under coverage and throughput constraints.

2023
GRETSI 2023

Prédiction de couvertures radio indoor avec des réseaux de neurones antagonistes génératifs

C. T. Cissé, O. Baala, V. Guillet, F. Spies, A. Caminada

XXIXe Colloque GRETSI sur le Traitement du Signal et des Images

French-language presentation of the conditional GAN approach to indoor radio coverage prediction.

2022
GRETSI 2022

Complétion par apprentissage profond de séries temporelles d'images multi-spectrales à partir d'images hyper-spectrales

C. T. Cissé, A. Alboody, M. Puigt, G. Roussel, V. Vantrepotte, C. Jamet, T. K. Tran

XXVIIIe Colloque GRETSI sur le Traitement du Signal et des Images

French-language presentation of the Sentinel-2/Sentinel-3 time-series completion method.