Mingyang Song's picture

3 15 1

Mingyang Song

hitsmy

·

AI & ML interests

LVLMs

Recent Activity

upvoted a paper 26 days ago

Diversity-Incentivized Exploration for Versatile Reasoning

upvoted a paper 26 days ago

Native Hybrid Attention for Efficient Sequence Modeling

upvoted a paper about 2 months ago

Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

View all activity

Organizations

Papers 3

arxiv:2505.08617

arxiv:2503.12821

arxiv:2501.03124

models 1

hitsmy/Qwen2-VL-2B-Instruct-SFT

Image-to-Text • 2B • Updated Mar 3 • 1

datasets 10

hitsmy/tool-pathverify-rl-v0

Viewer • Updated Aug 6 • 6k • 5

hitsmy/tool_pathverify_v0

Viewer • Updated Jul 25 • 896 • 33

hitsmy/tool_frozenlakev0

Preview • Updated Jul 21 • 16 • 1

hitsmy/tool_rlset_v1.1

Viewer • Updated Jul 10 • 31.5k • 53 • 1

hitsmy/tool_rlset_v1

Viewer • Updated Jul 6 • 31.5k • 110

hitsmy/OpenThinkIMG-Chart-RL-14501

Viewer • Updated May 24 • 14.5k • 79

hitsmy/OpenThinkIMG-Chart-Test-994

Viewer • Updated May 24 • 994 • 31

hitsmy/OpenThinkIMG-Chart-SFT-2942

Viewer • Updated May 22 • 2.94k • 109

hitsmy/toolrl_v1_gemmareachqa

Viewer • Updated May 8 • 15.5k • 9

hitsmy/PRMBench_Preview

Viewer • Updated Jan 7 • 6.22k • 51 • 4