Initialization Improves LLM-Driven Discovery
Paper • 2610.00707 • Published • 6
Mansi Sakarvadia
msakarvadia
·
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
Initialization Improves LLM-Driven Discovery authored a paper 4 days ago
Interpreting Language Model Hidden States at Scale authored a paper 4 days ago
Attention Lens: A Tool for Mechanistically Interpreting the Attention
Head Information Retrieval MechanismOrganizations
authored 7
papers 4 days ago
Interpreting Language Model Hidden States at Scale
Paper • 2608.10260 • Published
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism
Paper • 2310.16270 • Published • 1
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
Paper • 2309.05605 • Published • 1
Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning
Paper • 2412.06717 • Published
Mitigating Memorization In Language Models
Paper • 2410.02159 • Published
SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses
Paper • 2504.20405 • Published
upvoted a paper 4 days ago
upvoted a paper 4 months ago
liked 3
datasets over 2 years ago
updated a
dataset almost 3 years ago