Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better upvoted a paper about 7 hours ago
Priming: Hybrid State Space Models From Pre-trained Transformers upvoted a paper about 8 hours ago
ReplaySSM: Cache SSM Inputs, Not StateOrganizations
None yet