Parallel-R1-v2

AI & ML interests

None defined yet.

Recent Activity

Leo-Dai  authored a paper about 16 hours ago

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Leo-Dai  authored a paper about 16 hours ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Leo-Dai  submitted a paper about 22 hours ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

View all activity

Team members 3