4 13 6

Siyuan Huang

chamber111

AI & ML interests

None yet

Recent Activity

upvoted a paper about 8 hours ago

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

updated a dataset 22 days ago

chamber111/POPE-AOKVQA

published a dataset 22 days ago

chamber111/POPE-AOKVQA

View all activity

Organizations

Collections 2

Papers 3

arxiv:2510.09285

arxiv:2509.24304

arxiv:2503.01422

models 3

datasets 5

chamber111/POPE-AOKVQA

Viewer • Updated 22 days ago • 9k • 23

chamber111/POPE-GQA

Viewer • Updated 22 days ago • 9k • 75

chamber111/VPPO-Eval

Preview • Updated Oct 16, 2025 • 171 • 1

chamber111/VPPO_MMK12_validation

Viewer • Updated Oct 16, 2025 • 2k • 2.85k • 1

chamber111/VPPO_ViRL39K_train

Viewer • Updated Oct 16, 2025 • 38.9k • 1.27k • 1

Siyuan Huang

AI & ML interests

Recent Activity

Organizations

Collections 2

chamber111/VPPO_ViRL39K_train

chamber111/VPPO_MMK12_validation

chamber111/VPPO-Eval

Spotlight on Token Perception for Multimodal Reinforcement Learning

chamber111/VPPO-7B

chamber111/VPPO-32B

Spotlight on Token Perception for Multimodal Reinforcement Learning

chamber111/VPPO-8B

chamber111/VPPO_ViRL39K_train

chamber111/VPPO_MMK12_validation

chamber111/VPPO-Eval

Spotlight on Token Perception for Multimodal Reinforcement Learning

chamber111/VPPO-7B

chamber111/VPPO-32B

Spotlight on Token Perception for Multimodal Reinforcement Learning

chamber111/VPPO-8B

Papers 3

models 3

chamber111/VPPO-8B

chamber111/VPPO-7B

chamber111/VPPO-32B

datasets 5

chamber111/POPE-AOKVQA

chamber111/POPE-GQA

chamber111/VPPO-Eval

chamber111/VPPO_MMK12_validation

chamber111/VPPO_ViRL39K_train

Siyuan Huang

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 3

models 3 Sort: Recently updated

datasets 5 Sort: Recently updated

models 3

datasets 5