Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
Paper
•
2412.07334
•
Published
•
17
Pedro H. V. Valois
pvalois
AI & ML interests
Interpretability
Recent Activity
published
a dataset
3 months ago
pvalois/test
new activity
4 months ago
kernels-community/flash-attn3:Suport CUDA 12.8
Organizations
None yet
authored
a
paper
12 months ago
authored
3
papers
about 1 year ago
Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery
Paper
•
2403.01183
•
Published
Second-order difference subspace
Paper
•
2409.08563
•
Published
Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
Paper
•
2311.15022
•
Published