arxiv:2606.12397
Songhao Wu
shwu
AI & ML interests
Mixture-of-Experts Model, Language Model Pretraining
Recent Activity
upvoted a paper 2 days ago
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum submitted a paper 2 days ago
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum upvoted a paper 10 days ago
Inducing Process Supervision from Outcome-Only Reinforcement LearningOrganizations
None yet