🔄 In a Training Loop
Hunar Batra
hunarbatra
AI & ML interests
RL, Reasoning, Interpretability and Control, Embodied AI
Recent Activity
authored a paper 1 day ago
Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety liked a model 7 days ago
OX-PIXL/MMDiff_SAEs liked a dataset 12 days ago
hunarbatra/STVQA-7K