-
starriver030515/hapo_data
Viewer • Updated • 1.59k • 26 -
starriver030515/Qwen2.5-Math-1.5B-16k
Text Generation • 2B • Updated • 11 -
starriver030515/Qwen2.5-Math-7B-32k
Text Generation • 8B • Updated • 20 -
From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature
Paper • 2509.16591 • Published • 2
Zheng Liu
starriver030515
AI & ML interests
None yet
Recent Activity
published a bucket 7 days ago
starriver030515/OSWorld-Science-data-bucket upvoted a paper about 1 month ago
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression liked a model about 1 month ago
deepseek-ai/DeepSeek-V4.1-FlashOrganizations
-
starriver030515/FUSION-LLaMA3.1-8B
Image-Text-to-Text • 10B • Updated • 12 -
starriver030515/FUSION-X-LLaMA3.1-8B
Image-Text-to-Text • 11B • Updated • 11 -
starriver030515/FUSION-X-Phi3.5-3B
Image-Text-to-Text • 6B • Updated • 14 • 2 -
starriver030515/FUSION-Phi3.5-3B
Image-Text-to-Text • 5B • Updated • 10
-
starriver030515/hapo_data
Viewer • Updated • 1.59k • 26 -
starriver030515/Qwen2.5-Math-1.5B-16k
Text Generation • 2B • Updated • 11 -
starriver030515/Qwen2.5-Math-7B-32k
Text Generation • 8B • Updated • 20 -
From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature
Paper • 2509.16591 • Published • 2
-
starriver030515/FUSION-LLaMA3.1-8B
Image-Text-to-Text • 10B • Updated • 12 -
starriver030515/FUSION-X-LLaMA3.1-8B
Image-Text-to-Text • 11B • Updated • 11 -
starriver030515/FUSION-X-Phi3.5-3B
Image-Text-to-Text • 6B • Updated • 14 • 2 -
starriver030515/FUSION-Phi3.5-3B
Image-Text-to-Text • 5B • Updated • 10