Mingyang Song's picture

3 16 1

Mingyang Song

hitsmy

·

AI & ML interests

LVLMs

Recent Activity

upvoted a paper about 14 hours ago

VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation

upvoted a paper 3 months ago

Diversity-Incentivized Exploration for Versatile Reasoning

upvoted a paper 3 months ago

Native Hybrid Attention for Efficient Sequence Modeling

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 • 12

datasets 10

hitsmy/tool-pathverify-rl-v0

Viewer • Updated Aug 6 • 6k • 13

hitsmy/tool_pathverify_v0

Viewer • Updated Jul 25 • 896 • 679

hitsmy/tool_frozenlakev0

Preview • Updated Jul 21 • 1.29k • 1

hitsmy/tool_rlset_v1.1

Viewer • Updated Jul 10 • 31.5k • 62 • 1

hitsmy/tool_rlset_v1

Viewer • Updated Jul 6 • 31.5k • 103

hitsmy/OpenThinkIMG-Chart-RL-14501

Viewer • Updated May 24 • 14.5k • 38

hitsmy/OpenThinkIMG-Chart-Test-994

Viewer • Updated May 24 • 994 • 15

hitsmy/OpenThinkIMG-Chart-SFT-2942

Viewer • Updated May 22 • 2.94k • 56

hitsmy/toolrl_v1_gemmareachqa

Viewer • Updated May 8 • 15.5k • 7

hitsmy/PRMBench_Preview

Viewer • Updated Jan 7 • 6.22k • 175 • 4