From the 1 of 28 linked papers with an AI index.
28 papers
From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1
The paper proposes the Normalised Sensitivity Ratio (NSR), a post‑hoc, model‑agnostic method to distinguish causal from spurious features by comparing model sensitivity across envi…
Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1
Consider a model trained at a single hospital to predict patient recovery, where the measured feature bundles the patient's true health signal () with a systematic artefact…
Stress Testing Concept Erasure with Large Language Model Agents
Yuyang Xue, Feng Chen, Zhihua Liu +4
Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. However, verifying whether a model has…
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
Fabio De Sousa Ribeiro, Emma A. M. Stanley, Charles Jones +7
We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer…
CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs
Raman Dutt, Pedro Sanchez, Yongchen Yao +3
Structured benchmarks have advanced text-conditional image generation for real-world imagery, however, no such benchmark exists for synthetic radiograph generation. Despite being a…
MedVision: Benchmarking Quantitative Medical Image Analysis
Yongcheng Yao, Yongshuo Zong, Raman Dutt +3
Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks.…