Please wait while we prepare your content.
Unsolved research questions waiting for your expertise. Collaborate with the lab, claim a problem, or propose your own. Funding opportunities are attached to select problems.
Apply formal methods to prove properties of reward models used in RLHF, ensuring they preserve human intent under distribution shift.
Have an unsolved research question? Submit it to the board. If accepted, it becomes visible to the entire research community and may qualify for lab funding.
Submit a Research Question