arxiv:2504.07964
Zhongyang Li
Lzy01241010
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
How Instruction and Reasoning Data shape Post-Training: Data Quality
through the Lens of Layer-wise Gradients
authored
a paper
about 2 months ago
C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization
for Test-Time Expert Re-Mixing
Organizations
None yet
