Runpeng Dai
Leo-Dai
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Dream-RSI: Recursive Self-Improvement through Evolving Worlds authored a paper 12 days ago
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning authored a paper 12 days ago
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy DistillationOrganizations
models 17
Leo-Dai/PPO_BL_250_critic
4B • Updated • 4
Leo-Dai/PPO_BL_200_critic
Updated • 3
Leo-Dai/PPO_BL_300_actor
Updated • 5
Leo-Dai/PPO_BL_250_actor
Updated • 2
Leo-Dai/PPO_BL_300_critic
Updated
Leo-Dai/GRPO_BL_40
4B • Updated • 3
Leo-Dai/GRPO_BL_30
4B • Updated • 5
Leo-Dai/GRPO_BL_20
4B • Updated • 5
Leo-Dai/GRPO_BL_400
4B • Updated • 3
Leo-Dai/GRPO_BL_10
4B • Updated • 5