2 citations · 6 across the 18 of their papers we have counts for
19 papers
Large dust grains escaping from a supernova remnant
Evgenii O. Vasiliev
Dust grains produced in the supernova (SN) ejecta at early ages are partially destroyed in hot gas of the SN remnant. Large grains owing to their inertia can overtake the forward s…
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
Florian Rottach, Sebastian Schieferdecker, William Rudman +2
Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of bi…
Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models
Okan S. Coskun, Florian Rottach, Carsten Eickhoff +1
We investigate the geometry of decision-making in Multiple Choice Question Answering (MCQA) through the lens of isotropy. Analyzing five open-weight models across diverse datasets,…
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…
VESTA: Visual Exploration with Statistical Tool Agents
William Rudman, Abhishek Divekar, Kanishk Jain +6
Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-la…
What's in a Name? Morphological Shortcuts by LLMs in Pharmacology
Kaijie Mo, Thomas Yang, Chantal Shaib +6
The morphological form of a word can often give cues to its meaning, but purely relying on these mappings can lead to overgeneralization in high-stakes domains. In the medical doma…
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…
Multimodal QUD: Inquisitive Questions from Scientific Figures
Yating Wu, William Rudman, Venkata S Govindarajan +2
Discourse comprehension in complex documents often involves continuously posing and resolving Questions Under Discussion (QUDs). While QUD frameworks have so far focused on text, s…
When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
Jonathan Nemitz, Carsten Eickhoff, Junyi Jessy Li +3
Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere to their introspective reaso…
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…
From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
Florian Rottach, William Rudman, Bastian Rieck +2
Studying the shape of text embedding spaces enhances our understanding of model behavior and how geometry affects downstream task performance. While a range of topological and geom…
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…
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…
TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
Florentin Beck, William Rudman, Carsten Eickhoff
Large Language Models (LLMs) present significant computational and memory challenges due to their extensive size, making pruning essential for their efficient deployment. Existing…
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…
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,…
Outlier Dimensions Encode Task-Specific Knowledge
William Rudman, Catherine Chen, Carsten Eickhoff
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although…
Stable Anisotropic Regularization
William Rudman, Carsten Eickhoff
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that L…
Garden-Path Traversal in GPT-2
William Jurayj, William Rudman, Carsten Eickhoff
In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular. Studies examining the behavior of these models tend to focus…