William Rudman
Scholar

William Rudman

Google Scholar ID: KLFVnecAAAAJ
Postdoctoral Fellow, UT-Austin
Natural Language ProcessingVision Language ModelsAI
Google Scholar↗
Citations & Impact
All-time
Citations
106
 
H-index
6
 
i10-index
3
 
Publications
11
 
Co-authors
2
list available
Contact
No contact links provided.
Publications
8 items
When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
2026
Cited
0
Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
arXiv.org · 2026
Cited
0
From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
2025
Cited
0
APP: Accelerated Path Patching with Task-Specific Pruning
2025
Cited
0
TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
2025
Cited
0
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
2025
Cited
0
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
2025
Cited
0
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Noise-free Text-Image Corruption and Evaluation
arXiv.org · 2024
Cited
0
Resume (English only)
Co-authors
2 total
Carsten Eickhoff
Carsten Eickhoff
Professor, University of Tübingen
Nate Gillman
Nate Gillman
PhD student, ML @ Brown University