collaborators

5 papers

cs.LG2026

MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction

Marc Boubnovski Martell, Josefa Lia Stoisser, Lawrence Phillips +6

Predicting transcriptional responses to unseen genetic perturbations is essential for understanding gene regulation and prioritizing large-scale perturbation experiments. Existing…

cs.AI2025

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering

Josefa Lia Stoisser, Lawrence Phillips, Aditya Misra +5

Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches re…

cs.DB2025

Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries

Josefa Lia Stoisser, Marc Boubnovski Martell, Kaspar Märtens +4

Electronic health records (EHRs) contain richly structured, longitudinal data essential for predictive modeling, yet stringent privacy regulations (e.g., HIPAA, GDPR) often restric…

cs.AI2025

Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning

Josefa Lia Stoisser, Marc Boubnovski Martell, Lawrence Phillips +6

Large language model (LLM) agents are increasingly deployed in structured biomedical data environments, yet they often produce fluent but overconfident outputs when reasoning over…

cs.CL2025

STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing

Josefa Lia Stoisser, Marc Boubnovski Martell, Lawrence Phillips +2

We propose STRuCT-LLM, a unified framework for training large language models (LLMs) to perform structured reasoning over both relational and graph-structured data. Our approach jo…