arxiv:2505.13909
Jiahe Jin
zizi-0123
AI & ML interests
None yet
Recent Activity
upvoted a paper 12 days ago
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training upvoted a paper about 1 month ago
daVinci-Dev: Agent-native Mid-training for Software Engineering updated
a model about 2 months ago
zizi-0123/mhqa_llama_grpo Organizations
None yet
models 35
zizi-0123/mhqa_llama_grpo
Updated
zizi-0123/web_llama_sft_correct
Text Generation • 3B • Updated
zizi-0123/web_llama_sft_correct_grpo
Updated
zizi-0123/mhqa_llama_sft_behavior
Text Generation • 3B • Updated
• 1
zizi-0123/mhqa_llama_sft_behavior_grpo
Updated
zizi-0123/OLMo2-1B-midtrain-run1
1B • Updated
• 2
zizi-0123/mhqa_llama_sft_random_grpo
Updated
zizi-0123/mhqa_llama_sft_correct_grpo
Updated
zizi-0123/web_qwen_sft_singlebehavior_grpo
Updated
zizi-0123/web_llama_sft_random_grpo
Updated
datasets 0
None public yet