🏢 Dartmouth College
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
·5008 words·24 mins·
loading
·
loading
Computer Vision
Image Classification
🏢 Dartmouth College
ProtoViT: a novel interpretable image classification method using Vision Transformers and adaptive prototypes, achieving higher accuracy and providing clear explanations.
Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
·2605 words·13 mins·
loading
·
loading
AI Generated
Machine Learning
Representation Learning
🏢 Dartmouth College
Boost GNN graph classification accuracy by enforcing consistency in learned representations across layers using a novel loss function!
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
·3306 words·16 mins·
loading
·
loading
Natural Language Processing
Large Language Models
🏢 Dartmouth College
DARG dynamically evaluates LLMs via adaptive reasoning graphs, revealing performance drops with increased complexity and exposing model biases.