Mingyang Song

hitsmy

·

AI & ML interests

LVLMs

Recent Activity

upvoted a paper 1 day ago

Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

liked a model 16 days ago

moonshotai/Kimi-K3

authored a paper 25 days ago

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

View all activity

Organizations

hitsmy 's datasets 10

hitsmy/tool-pathverify-rl-v0

Viewer • Updated Aug 6, 2025 • 6k • 39

hitsmy/tool_pathverify_v0

Viewer • Updated Jul 25, 2025 • 896 • 119

hitsmy/tool_frozenlakev0

Preview • Updated Jul 21, 2025 • 20 • 1

hitsmy/tool_rlset_v1.1

Viewer • Updated Jul 10, 2025 • 31.5k • 25 • 1

hitsmy/tool_rlset_v1

Viewer • Updated Jul 6, 2025 • 31.5k • 233

hitsmy/OpenThinkIMG-Chart-RL-14501

Viewer • Updated May 24, 2025 • 14.5k • 33

hitsmy/OpenThinkIMG-Chart-Test-994

Viewer • Updated May 24, 2025 • 994 • 25

hitsmy/OpenThinkIMG-Chart-SFT-2942

Viewer • Updated May 22, 2025 • 2.94k • 32 • 1

hitsmy/toolrl_v1_gemmareachqa

Viewer • Updated May 8, 2025 • 15.5k • 34

hitsmy/PRMBench_Preview

Viewer • Updated Jan 7, 2025 • 6.22k • 388 • 6