ICDM 2026 — OWAD Workshop
The Blind Spot Paradox has been accepted at the OWAD workshop during IEEE ICDM 2026, November 12–15 in Shenyang, China.
CIKM 2026
Two papers from the Lusis chair will be presented at CIKM 2026 in Rome: kernel-based anomaly detection and knowledge-informed causal discovery.
Fraud Campaign Detection and Rule Learning for Card Payments
Investigate whether transaction groups and interpretable rules, including rules proposed by language models, improve future fraud detection beyond a LightGBM baseline.
Relational steering for tabular anomaly detection
Investigating whether context-dependent interventions in tabular models reveal anomalies that violate relationships between variables.
ESANN 2026
José Lucas De Melo Costa will attend ESANN 2026 in Bruges to present “High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models”.
Flow Matching for Credit Card Fraud Detection
Evaluate one-step flow matching for credit card fraud detection, comparing classification quality, training cost and inference speed with gradient boosted trees.
ICLR 2025
José Lucas De Melo Costa, Bich-Liên Doan and Fabrice Popineau will attend ICLR2025 in Singapour to present T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data Hugo Thimonier, who is now at Emobot, will be there too.
ILB 2025
José Lucas De Melo Costa, Fabrice Daniel and Fabrice Popineau are presenting Comparative Evaluation of Anomaly Detection Methods for Fraud Detection in Online Credit Card Payments at the 18th Financial Risks International Forum in Paris organized by Institut Louis Bachelier.
More about the event:
Day 1 kick off Day 1 parallel sessions Day 1 wrap-up 2nd day kick off 2nd day parallel sessions
CIKM 2024
Fabrice Popineau is at CIKM2024 in Boise, Idaho to present Retrieval Augmented Deep Anomaly Detection for tabular Data.