Skip to Main Content

Research

My research focuses on mechanistic interpretability and AI alignment. I study why interpretability methods fail to generalize across models and tasks, and build reliable tools to detect deception and misalignment inside large language models.

Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs

Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs

Kipngeno Koech, Muhammad Adam, Baimam Boukar Jean Jacques, Joao Barros

LLM AgentsAI SafetySafety GatesEvaluationPreprint
An Adaptive Latent Semantic Analysis Framework for Binary Text Classification

An Adaptive Latent Semantic Analysis Framework for Binary Text Classification

Baimam Boukar Jean Jacques, Isaac Touza, Kaladzavi Guidedi

International Journal of Information Management

NLPLatent Semantic AnalysisInterpretabilityText ClassificationSubmitted
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding

Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding

Baimam Boukar Jean Jacques, Brandone Fonya, Nchofon Tagha Ghogomu, Pauline Nyaboe, Kipngeno Koech

EEGBrain-Computer InterfacesZero-Shot LearningNeural DecodingPreprint
Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

Allassan Tchangmena A Nken, Baimam Boukar Jean Jacques, Miriam Rateike, Celia Cintas, Skyler Speakman

AAAI 2026 Workshop on New Frontiers in Information Retrieval

Information RetrievalDeepScanLLM EmbeddingsAnomalous PatternPreprint
Mapping Socioeconomic Air Quality Disparities In Rwanda Using Sentinel-5P TROPOMI Data In Google Earth Engine

Mapping Socioeconomic Air Quality Disparities In Rwanda Using Sentinel-5P TROPOMI Data In Google Earth Engine

Baimam Boukar Jean Jacques, Kamikazi Ndayizeye Raissa, Umubyeyi Evelyne, Bertinn Ndahayo Singizwa, Emily Aiken

IEEE MIGARS 2025

Air QualityRemote SensingGoogle EEPublished
Explainable Deep-Learning Based Potentially Hazardous Asteroids Classification Using Graph Neural Networks

Explainable Deep-Learning Based Potentially Hazardous Asteroids Classification Using Graph Neural Networks

Baimam Boukar Jean Jacques

Harvard AstroAI Workshop 2025.

SpaceAIAstrophysicsPresented