Large Language Models as Markov Chains
Paper
• 2410.02724 • Published
• 33 •
3
Ambroise Odonnat
ambroiseodt
AI & ML interests
Transformers, distribution shifts, optimization
Recent Activity
submitted
a paper
about 16 hours ago
Layer by layer, module by module: Choose both for optimal OOD probing of ViT authored
a paper
about 17 hours ago
Layer by layer, module by module: Choose both for optimal OOD probing of ViT authored
a paper
about 17 hours ago
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift Organizations
commented a paper over 1 year ago