William Rudman

According to our database, William Rudman authored at least 20 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Multimodal QUD: Inquisitive Questions from Scientific Figures.

Yating Wu, William Rudman, Venkata S. Govindarajan, Alexandros G. Dimakis, Junyi Jessy Li

CoRR, April, 2026

Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models.

Oliver McLaughlin, Daniel Shubin, Carsten Eickhoff, Ritambhara Singh, William Rudman, Michal Golovanevsky

CoRR, April, 2026

When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't.

Jonathan Nemitz, Carsten Eickhoff, Junyi Jessy Li, Kyle Mahowald, Michal Golovanevsky, William Rudman

CoRR, April, 2026

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models.

William Rudman, Michal Golovanevsky, Dana Arad, Yonatan Belinkov, Ritambhara Singh, Carsten Eickhoff, Kyle Mahowald

CoRR, January, 2026

2025

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures.

Florian Rottach, William Rudman, Bastian Rieck, Harrisen Scells, Carsten Eickhoff

CoRR, November, 2025

APP: Accelerated Path Patching with Task-Specific Pruning.

Frauke Andersen, William Rudman, Ruochen Zhang, Carsten Eickhoff

CoRR, November, 2025

TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning.

Florentin Beck, William Rudman, Carsten Eickhoff

CoRR, May, 2025

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind.

William Rudman, Michal Golovanesky, Amir Bar, Vedant Palit, Yann LeCun, Carsten Eickhoff, Ritambhara Singh

CoRR, February, 2025

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation.

Michal Golovanevsky, William Rudman, Vedant Palit, Carsten Eickhoff, Ritambhara Singh

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts.

Michal Golovanevsky, William Rudman, Michael A. Lepori, Amir Bar, Ritambhara Singh, Carsten Eickhoff

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind.

William Rudman, Michal Golovanevsky, Amir Bar, Vedant Palit, Yann LeCun, Carsten Eickhoff, Ritambhara Singh

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Noise-free Text-Image Corruption and Evaluation.

Michal Golovanevsky, William Rudman, Vedant Palit, Ritambhara Singh, Carsten Eickhoff

CoRR, 2024

Stable Anisotropic Regularization.

William Rudman, Carsten Eickhoff

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Outlier Dimensions Encode Task Specific Knowledge.

William Rudman, Catherine Chen, Carsten Eickhoff

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Leveraging Unlabeled Electroencephalographic Data to Predict Neurological Recovery for Comatose Patients Following Cardiac Arrest.

Isaac Sears, Augusto Garcia-Agundez, George Zerveas, William Rudman, Laura Mercurio, Corey E. Ventetuolo, Adeel Abbasi, Carsten Eickhoff

Proceedings of the Computing in Cardiology, 2023

2022

Garden-Path Traversal within GPT-2.

William Jurayj, William Rudman, Carsten Eickhoff

CoRR, 2022

ACQuA: Anomaly Classification with Quasi-Attractors.

William Rudman, Jack Merullo, Laura Mercurio, Carsten Eickhoff

Proceedings of the Computing in Cardiology, 2022

Garden Path Traversal in GPT-2.

William Jurayj, William Rudman, Carsten Eickhoff

Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022

IsoScore: Measuring the Uniformity of Embedding Space Utilization.

William Rudman, Nate Gillman, Taylor Rayne, Carsten Eickhoff

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022

2021

IsoScore: Measuring the Uniformity of Vector Space Utilization.

William Rudman, Nate Gillman, Taylor Rayne, Carsten Eickhoff

CoRR, 2021