Runpeng Dai
Leo-Dai
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification authored a paper 1 day ago
Reinforcing Multimodal Reasoning Against Visual Degradation authored a paper 1 day ago
G-Zero: Self-Play for Open-Ended Generation from Zero DataOrganizations
models 17
Leo-Dai/PPO_BL_250_critic
4B • Updated • 1
Leo-Dai/PPO_BL_200_critic
Updated • 2
Leo-Dai/PPO_BL_300_actor
Updated • 1
Leo-Dai/PPO_BL_250_actor
Updated • 1
Leo-Dai/PPO_BL_300_critic
Updated
Leo-Dai/GRPO_BL_40
4B • Updated • 1
Leo-Dai/GRPO_BL_30
4B • Updated • 1
Leo-Dai/GRPO_BL_20
4B • Updated • 1
Leo-Dai/GRPO_BL_400
4B • Updated • 1
Leo-Dai/GRPO_BL_10
4B • Updated • 1