AdaReasoner: Models and Datasets
Mingyang Song
hitsmy
AI & ML interests
LVLMs
Recent Activity
updated a dataset 1 day ago
AdaptivePolicy/adaptive-policy-v2.5-reason-mini published a dataset 1 day ago
AdaptivePolicy/adaptive-policy-v2.5-reason-mini upvoted an article 20 days ago
Your MoE Model Does Not Have to Select Fixed Number of ExpertsOrganizations
datasets 10
hitsmy/tool-pathverify-rl-v0
Viewer • Updated • 6k • 16
hitsmy/tool_pathverify_v0
Viewer • Updated • 896 • 12
hitsmy/tool_frozenlakev0
Preview • Updated • 9 • 1
hitsmy/tool_rlset_v1.1
Viewer • Updated • 31.5k • 70 • 1
hitsmy/tool_rlset_v1
Viewer • Updated • 31.5k • 47
hitsmy/OpenThinkIMG-Chart-RL-14501
Viewer • Updated • 14.5k • 24
hitsmy/OpenThinkIMG-Chart-Test-994
Viewer • Updated • 994 • 37
hitsmy/OpenThinkIMG-Chart-SFT-2942
Viewer • Updated • 2.94k • 96
hitsmy/toolrl_v1_gemmareachqa
Viewer • Updated • 15.5k • 7
hitsmy/PRMBench_Preview
Viewer • Updated • 6.22k • 88 • 4