Picture for Satya Lokam

Satya Lokam

Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model

Add code
Oct 21, 2024
Viaarxiv icon

SLIP: Securing LLMs IP Using Weights Decomposition

Add code
Jul 15, 2024
Figure 1 for SLIP: Securing LLMs IP Using Weights Decomposition
Figure 2 for SLIP: Securing LLMs IP Using Weights Decomposition
Figure 3 for SLIP: Securing LLMs IP Using Weights Decomposition
Figure 4 for SLIP: Securing LLMs IP Using Weights Decomposition
Viaarxiv icon

Non-Asymptotic Lower Bounds For Training Data Reconstruction

Add code
Apr 11, 2023
Viaarxiv icon