Lena Prasad
lprasad21
AI & ML interests
mechanistic interpretability, constitutional AI, candidate generation
Recent Activity
liked a dataset about 13 hours ago
ctang/HarmfulVsEthical_redteaming_eval_v3 upvoted a paper about 13 hours ago
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment liked a dataset 1 day ago
Cleanlab/FinQA-hallucination-detectionOrganizations
None yet