zhu

xuekai

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 17 hours ago

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

upvoted a paper 2 months ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

upvoted a paper 4 months ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

View all activity

Organizations

Papers 16

arxiv:2509.15207

arxiv:2509.09674

arxiv:2509.08827

arxiv:2509.04419

models 3

xuekai/FlowRL-DeepSeek-7B-code

8B • Updated Oct 27, 2025 • 2

xuekai/FlowRL-Qwen2.5-32B-math

33B • Updated Oct 27, 2025 • 7

xuekai/FlowRL-Qwen2.5-7B-math

8B • Updated Oct 27, 2025 • 3

datasets 2

xuekai/flowrl-data-collection

Preview • Updated Sep 28, 2025 • 110

xuekai/pad_train

Viewer • Updated Mar 21, 2024 • 184k • 14