arxiv:2510.18855
zhangzhenduo
ericzdzhang
ยท
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality
Data for Efficient and Accurate Code LLM
authored
a paper
about 2 months ago
Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning
for LLMs
authored
a paper
about 2 months ago
Towards High Data Efficiency in Reinforcement Learning with Verifiable
Reward
Organizations
None yet
models
0
None public yet
datasets
0
None public yet