This is your work, valued
PhD at CMU Machine Learning Department
GRASS. GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
10DynamicSAEGuardrails. Code for the paper "SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs"
8CoRAG. CoRAG is a framework extending RAG to collaborative settings
4subliminal-learning. Python
1aashiqmuhamed.github.io. Academic website
1dl-grasp-detection. Python
1