arxiv:2503.05132
Hengguang Zhou PRO
Dolphin42
AI & ML interests
Multi-modal Multi-agent Systems
Recent Activity
upvoted a paper about 9 hours ago
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards upvoted a paper about 9 hours ago
ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning upvoted a paper 10 days ago
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion ReinforcementOrganizations
models 6
Dolphin42/Qwen3-VL-8B-frozenlake-GRPO-vanilla-step5672
9B • Updated • 6
Dolphin42/Qwen3-VL-8B-frozenlake-GRPO-directonly-step1400
9B • Updated • 6
Dolphin42/Qwen3-VL-8B-frozenlake-GRPO-toolonly-step200
9B • Updated • 6
Dolphin42/Qwen3-VL-8B-spagent-SFT-v3layout
9B • Updated • 9
Dolphin42/Qwen3-VL-4B-spagent-SFT-v3
4B • Updated • 3
Dolphin42/Qwen2-VL-2B-SFT-MCPcoldstart-1012
Image-Text-to-Text • 2B • Updated • 17
datasets 16
Dolphin42/training_set
Updated • 14
Dolphin42/boundary
Updated • 8
Dolphin42/dscoder-1p3b-prompted-normal-fixed-7bdata-cot
Viewer • Updated • 288 • 7
Dolphin42/dscoder-1p3b-pfc-prompted-hardcode-fixed-7bdata-cot-167
Preview • Updated • 6
Dolphin42/dscoder-1p3b-pfc-prompted-skip-fixed-7bdata-cot
Viewer • Updated • 194 • 14
Dolphin42/dscoder-1p3b-pfc-prompted-modify-fixed-7bdata-cot
Viewer • Updated • 186 • 6
Dolphin42/dscoder-1p3b-pfc-prompted-hardcode-fixed-7bdata-cot
Preview • Updated • 15
Dolphin42/7B-pfc-prompted-modify-fixed-7bdata-cot-75
Viewer • Updated • 75 • 4
Dolphin42/7B-pfc-prompted-hardcode-fixed-7bdata-cot-36
Viewer • Updated • 36 • 7
Dolphin42/7B-pfc-prompted-skip-fixed-7bdata-cot-1086
Viewer • Updated • 1.09k • 5