William Rudman
8 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
๐ Cross-Pollinator (15) ๐ Conference Polyglot (4) ๐ Renaissance Researcher (5) ๐ Interdisciplinary Bridge ๐บ๏ธ Taxonomy Completionist (17)
๐งญ
Keyword Pioneer
๐ฃ
Hot Topic Early Bird
๐
Keyword Champion
(2)
โ
The Questioner
Conferences
ACL (3)
EMNLP (3)
ICLR (1)
NAACL (1)
Top co-authors
Keywords
vision-language model
(3)
embedding analysis
(2)
mechanistic interpretability
(2)
attention head
(2)
cosine similarity
(2)
vector space
(1)
geometric reasoning
(1)
hidden state
(1)
multimodal large language model
(1)
chain-of-thought prompting
(1)
multimodal reasoning
(1)
cross-attention mechanism
(1)
transformer decoder
(1)
knowledge prior
(1)
word embedding
(1)
activation steering
(1)
model prediction
(1)
surprisal analysis
(1)
syntactic ambiguity
(1)
large language model
(1)
Papers
Mechanisms of Prompt-Induced Hallucination in VisionโLanguage Models
ACL 2026
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
ACL 2025
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
EMNLP 2025
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
NAACL 2025
Stable Anisotropic Regularization
ICLR 2024
Outlier Dimensions Encode Task Specific Knowledge
EMNLP 2023
IsoScore: Measuring the Uniformity of Embedding Space Utilization
ACL 2022
Garden Path Traversal in GPT-2
EMNLP 2022