arxiv:2602.04804
Ding Yue
dingyue1011
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement LearningOrganizations
None yet
models 7
dingyue1011/OmniSIFT-7B
Updated • 1
dingyue1011/Qwen3-8B_Star1K_GRPO_Epoch5_bsz24
8B • Updated • 3
dingyue1011/Qwen3-8B_Star1K_GRPO_Epoch3_bsz24
8B • Updated • 2
dingyue1011/Qwen7B_Star1K_GRPO_Epoch5_bsz24
8B • Updated
dingyue1011/Qwen7B_Star1K_GRPO_Epoch3_bsz24
8B • Updated
dingyue1011/Llama8B_Star1K_GRPO_Epoch5_bsz24
8B • Updated
dingyue1011/Llama8B_Star1K_GRPO_Epoch3_bsz24
8B • Updated