Video
Unknown · 0:00
VPO (Vector Policy Optimization), a method from Ryan at MIT's Improbable AI Lab, changes RL post-training so a language model learns to produce several different good answers instead of one. Standard GRPO sums the rew...
Unknown · 0:00
VPO (Vector Policy Optimization), a method from Ryan at MIT's Improbable AI Lab, changes RL post-training so a language model learns to produce several different good answers instead of one. Standard GRPO sums the rew...
Redirecting...