Zhikun Xu

JerrrrryKun

·

https://jerrrrykun.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 10 days ago

Skill Reuse as Compression in Agentic RL

authored a paper 10 days ago

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

updated a model 9 months ago

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-2-1epoch500steps

View all activity

Organizations

None yet

Papers 5

arxiv:2605.31509

arxiv:2604.03472

arxiv:2506.13502

arxiv:2502.10454

models 25

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-2-1epoch500steps

Text Generation • 8B • Updated Nov 25, 2025 • 5

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-2-300steps

Text Generation • 8B • Updated Nov 24, 2025 • 6

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-2-200steps

Text Generation • 8B • Updated Nov 24, 2025 • 6

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-2-100steps

Text Generation • 8B • Updated Nov 24, 2025 • 5

JerrrrryKun/DeepSeek-R1-Distill-Qwen-7B-ER-v1-1-1430steps

Text Generation • 8B • Updated Nov 24, 2025 • 4

JerrrrryKun/Qwen2.5-Math-7B-Instruct-LLM4Math-V2data-Sequential-perturbationsignalonly-ispass-400steps

Text Generation • 8B • Updated Oct 7, 2025 • 4

JerrrrryKun/Llama-3.1-8B-Instruct-LLM4Math-V2data-Sequential-vanillaRL-200steps

Text Generation • 8B • Updated Oct 6, 2025 • 4

JerrrrryKun/Llama-3.1-8B-Instruct-LLM4Math-V2data-Sequential-perturbationsignalonly-200steps

Text Generation • 8B • Updated Oct 6, 2025 • 5

JerrrrryKun/Llama-3.1-8B-Instruct-LLM4Math-V2data-Sequential-vanillaRL-100steps

Text Generation • 8B • Updated Oct 6, 2025 • 3

JerrrrryKun/Llama-3.1-8B-Instruct-LLM4Math-V2data-Sequential-perturbationsignalonly-100steps

Text Generation • 8B • Updated Oct 6, 2025 • 3

datasets 0

None public yet