3 papers
cs.CL2025
Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors
Dane Williamson, Yangfeng Ji, Matthew Dwyer
Large Language Models (LLMs) demonstrate strong mathematical problem-solving abilities but frequently fail on problems that deviate syntactically from their training distribution.…
cs.CV2025
CASE: Contrastive Activation for Saliency Estimation
Dane Williamson, Yangfeng Ji, Matthew Dwyer
Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility can obscure critical limitations.…
cs.LG2025
Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection
Dane Williamson, Yangfeng Ji, Matthew Dwyer
Out-of-distribution (OOD) detection is a critical task in machine learning, particularly for safety-critical applications where unexpected inputs must be reliably flagged. While hi…