|
Literature Review
Interpretability
1 Sep 2024 [Post] [Arxiv] |
Review on "Multilevel Interpretability Of Artificial Neural Networks"Lessons from neuroscience |
|
Study
Incontext
16 Aug 2024 [Post] [ICML 2024] |
Review on "In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering"How to steer hidden representation in GPT. |
|
Literature Review
Copyright Issue
16 Jul 2024 [Post] [Arxiv] |
Review on "What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation"The emergence of induction heads in training GPT. |
|
Literature Review
Copyright Issue
15 Jul 2024 [Post] [Scholar] |
Review on "The Files are in the Computer: Copyright, Memorization, and Generative-AI Systems"Copyright is one of the most important issues in the realm of generative AI. |
|
Literature Review
Mechanistic Interpretability
14 Jul 2024 [Post] [Arxiv] |
Review on Explicit Memory for Language Modeling ($\text{Memory}^3$)Literature reviews for memory architecture in neural networks |
|
Literature Review
Mechanistic Interpretability
13 Jul 2024 [Post] [OpenReview] |
Review on dictionary learning for mechanistic interpretability in ICML 2024Literature reviews on ICML 2024 mechanistic interpretability workshop oral and spotlight papers. |
|
Literature Review
Mechanistic Interpretability
13 Jul 2024 [Post] [OpenReview] |
Review on causality for mechanistic interpretability in ICML 2024Literature reviews on ICML 2024 mechanistic interpretability workshop oral and spotlight papers. |