8 citations · 10 across the 11 of their papers we have counts for
12 papers
Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models
Niclas Lietzow, Danielle Bitterman, Carsten Eickhoff +2
Vision-language models must reconcile visual evidence with memorized world knowledge when the two conflict. How they resolve this conflict shapes the reliability of multimodal syst…
Scientific Domain Knowledge Improves Vision-Language Fundus Models
Verena Jasmin Hallitschke, Carsten Eickhoff, Philipp Berens
Vision-language models hold considerable promise for ophthalmology, but it remains unclear which training data source best conveys expert domain knowledge. Existing ophthalmic mode…
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…
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…
APP: Accelerated Path Patching with Task-Specific Pruning
Frauke Andersen, William Rudman, Ruochen Zhang +1
Circuit discovery is a key step in many mechanistic interpretability pipelines. Current methods, such as Path Patching, are computationally expensive and have limited in-depth circ…
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…
Crosslingual Reasoning through Test-Time Scaling
Zheng-Xin Yong, M. Farid Adilazuarda, Jonibek Mansurov +7
Reasoning capabilities of large language models are primarily studied for English, even when pretrained models are multilingual. In this work, we investigate to what extent English…
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…
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
Reza Esfandiarpoor, George Zerveas, Ruochen Zhang +3
Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels,…
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…