Vedang Lad

vedanglad's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 2 months ago

Opening the AI black box: program synthesis via mechanistic interpretability

Paper • 2402.05110 • Published Feb 7, 2024 • 2

The Remarkable Robustness of LLMs: Stages of Inference?

Paper • 2406.19384 • Published Jun 27, 2024