jwjeonn/GRPO-Qwen-Qwen3-4B-dapo_math
Updated
Jiwon Jeon
jwjeonn
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR updated a model 5 days ago
jwjeonn/GRPO-Qwen-Qwen3-4B-dapo_math published a model 5 days ago
jwjeonn/GRPO-Qwen-Qwen3-4B-dapo_mathOrganizations
None yet
models 19
jwjeonn/SDPO-Qwen-Qwen3-4B-deepscaler_math-reprompt-tur0.0
Updated
jwjeonn/SDPO-Qwen-Qwen3-4B-dapo_math-reprompt-tur0.0
Updated
jwjeonn/SDPO20-kl-sdpobottom20-Qwen3-4B-dapo_math-origPrompt
Updated
jwjeonn/iterWsdpo_review-grpo20-maxbuff2000-sdpoepoch2-Qwen3-4B-dapo_math-reprompt-tur0.0_persist
Updated
jwjeonn/IterWSDPO-grpo20-sdpo20-Qwen3-4B-dapo_math-org-prompt-tur0.0
Updated
jwjeonn/GRPO-Qwen-Qwen3-4B-dapo_math-reprompt
Updated
jwjeonn/GRPO-Qwen-Qwen3-4B-Instruct-2507-dapo_math-reprompt
Updated
jwjeonn/IterSDPO-grpo30-sdpo10-Qwen3-4B-deepscaler_math
Updated
jwjeonn/SDPO-Qwen-Qwen3-4B-Instruct-2507-dapo_math-reprompt-tur0.0
Updated