Leo-Dai/PPO_BL_250_critic
4B • Updated • 2
Runpeng Dai
Leo-Dai
AI & ML interests
None yet
Recent Activity
authored a paper 11 days ago
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning authored a paper 11 days ago
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy DistillationOrganizations
Leo-Dai/PPO_BL_200_critic
Updated • 2
Leo-Dai/PPO_BL_300_actor
Updated • 4
Leo-Dai/PPO_BL_250_actor
Updated • 2
Leo-Dai/PPO_BL_300_critic
Updated
Leo-Dai/GRPO_BL_40
4B • Updated • 1
Leo-Dai/GRPO_BL_30
4B • Updated • 4
Leo-Dai/GRPO_BL_20
4B • Updated • 3
Leo-Dai/GRPO_BL_400
4B • Updated • 2
Leo-Dai/GRPO_BL_10
4B • Updated • 5
Leo-Dai/GRPO_BL_350
4B • Updated • 1
Leo-Dai/GRPO_BL_200
4B • Updated • 2
Leo-Dai/GRPO_BL_150
4B • Updated • 2
Leo-Dai/GRPO_BL_100
4B • Updated • 3
Leo-Dai/GRPO_BL_300
4B • Updated • 3
Leo-Dai/GRPO_BL_250
4B • Updated • 2
Leo-Dai/GRPO_BL_50
4B • Updated • 2