10 citations · 22 across the 12 of their papers we have counts for
13 papers
A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support
Ioanna Gemou, Matteo Gamba, Randall Balestriero +1
Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning sys…
Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling
Andrew Wang, Ellie Pavlick, Ritambhara Singh
An active challenge in developing multimodal machine learning (ML) models for healthcare is handling missing modalities during training and deployment. As clinical datasets are inh…
Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
Oliver McLaughlin, Daniel Shubin, Carsten Eickhoff +3
Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, p…
The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models
Tassallah Abdullahi, Shrestha Ghosh, Hamish S Fraser +5
Persona conditioning can be viewed as a behavioral prior for large language models (LLMs) and is often assumed to confer expertise and improve safety in a monotonic manner. However…
UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages
Tassallah Abdullahi, Macton Mgonzo, Mardiyyah Oduwole +4
Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerable to evolving harms, cross-ling…
Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
William Rudman, Michal Golovanevsky, Dana Arad +4
Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-co…
PiCME: Pipeline for Contrastive Modality Evaluation and Encoding in the MIMIC Dataset
Michal Golovanevsky, Pranav Mahableshwarkar, Carsten Eickhoff +1
Multimodal deep learning holds promise for improving clinical prediction by integrating diverse patient data, including text, imaging, time-series, and structured demographics. Con…
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
Michal Golovanevsky, William Rudman, Michael Lepori +3
Multimodal Large Language Models (MLLMs) perform well on tasks such as visual question answering, but it remains unclear whether their reasoning relies more on memorized world know…
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
William Rudman, Michal Golovanevsky, Amir Bar +4
Despite strong performance on vision-language tasks, Multimodal Large Language Models (MLLMs) struggle with mathematical problem-solving, with both open-source and state-of-the-art…
K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction
Tassallah Abdullahi, Ioanna Gemou, Nihal V. Nayak +4
Biomedical knowledge graphs (KGs) encode rich, structured information critical for drug discovery tasks, but extracting meaningful insights from large-scale KGs remains challenging…
Retrieval Augmented Zero-Shot Text Classification
Tassallah Abdullahi, Ritambhara Singh, Carsten Eickhoff
Zero-shot text learning enables text classifiers to handle unseen classes efficiently, alleviating the need for task-specific training data. A simple approach often relies on compa…
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
Michal Golovanevsky, William Rudman, Vedant Palit +2
Vision-Language Models (VLMs) have gained community-spanning prominence due to their ability to integrate visual and textual inputs to perform complex tasks. Despite their success,…
On the Effect of Image Resolution on Semantic Segmentation
Ritambhara Singh, Abhishek Jain, Pietro Perona +2
High-resolution semantic segmentation requires substantial computational resources. Traditional approaches in the field typically downscale the input images before processing and t…