Skip to content
Cheick T. Cissé
fr

Research Scientist, Generative AI

Cheick Tidiani Cissé

I build generative models that leave the lab — diffusion and GANs for radio maps, transformers for low-resource translation, sequence models for human mobility.

Findings of ACL 2026PhD · Orange ResearchReviewer · NeurIPS, AAAI
Read the researchSee selected work
Open to research conversations
Cheick Tidiani Cissé
8
Peer-reviewed papers
1
Patent filed
5
Years in research
2
Years teaching

Selected work

What I work on

Language

Kumatigi — French↔Bambara translation corpus

A 67k quality-scored parallel corpus for a language with almost no machine-readable data, released openly and published at Findings of ACL 2026.

Sentence pairs
67k
BLEU gain
+3–4

Vision

Generative radio maps for indoor Wi-Fi planning

cGAN, diffusion and physics-informed ResUNet models that predict Wi-Fi coverage from a floor plan in place of ray-tracing simulation. Patent filed; Top-5 at the ICASSP 2025 Grand Challenge.

Prediction error
2.5 dB RMSE
ICASSP Grand Challenge
Top-5 / 16+

Sequences

Synthetic mobility traces with generative transformers

Transformer-based generative models that produce realistic human-mobility trajectories, so operator data can be exploited without exposing real subscribers.

Recent

Findings of ACL 2026Sole author+3–4 BLEU

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

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.

PaperPDFDataset

Peer review

AAAI 2027NeurIPS 2026

Let’s talk

I’m always glad to talk about generative modelling, low-resource NLP, or research roles. The fastest route is email.

Get in touchCV