Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
xuxin
xx18
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 days ago
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
updated
a model
about 1 month ago
xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3
Organizations
models
15
xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3
Text Generation
•
4B
•
Updated
•
4
xx18/DirectRL_Qwen3-4B_baseline2
Text Generation
•
4B
•
Updated
•
2
xx18/DirectRL_Qwen3-4B_baseline1
Text Generation
•
4B
•
Updated
•
7
xx18/TFPI-Qwen3-4B-Stage3_then_RL
Text Generation
•
4B
•
Updated
•
9
xx18/TFPI-Qwen3-4B-Stage3
Text Generation
•
4B
•
Updated
•
6
xx18/TFPI-Qwen3-4B-Stage2
Text Generation
•
4B
•
Updated
•
6
xx18/TFPI-Qwen3-4B-Stage1
Text Generation
•
4B
•
Updated
•
4
xx18/DirectRL_DeepSeek-Qwen-1.5B_baseline2
Text Generation
•
2B
•
Updated
•
1
xx18/DirectRL_DeepSeek-Qwen-1.5B_baseline1
Text Generation
•
2B
•
Updated
•
5
xx18/TFPI-DeepSeek-Qwen-1.5B-Stage3_then_RL
Text Generation
•
2B
•
Updated
•
5