JeonghyeKim
beanie00
AI & ML interests
None yet
Recent Activity
authored a paper about 20 hours ago
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR commentedon a paper 3 months ago
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVROrganizations
None yet
models 12
beanie00/math-SDPO-Qwen3-8B-think-off-step-100
8B • Updated
beanie00/math-GRPO-Qwen3-8B-think-off-step-100
8B • Updated • 4
beanie00/math-GRPO-DeepSeek-Distill-7B-step-100
8B • Updated • 4
beanie00/math-SDPO-no-think-contents-DeepSeek-Distill-7B-step-100
8B • Updated • 4
beanie00/math-SDPO-DeepSeek-Distill-7B-step-100
8B • Updated • 8
beanie00/math-SDPO-Qwen3-8B-think-step-100
8B • Updated • 5
beanie00/math-SDPO-no-think-contents-Qwen3-8B-think-step-100
8B • Updated • 3
beanie00/math-GRPO-Qwen3-8B-think-step-100
8B • Updated • 5
beanie00/Qwen2.5-Math-7B_sft_v1
333k • Updated • 6
beanie00/Qwen2.5-7B_sft_v1
333k • Updated • 8
datasets 0
None public yet