Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 258
Hangzhou Vision Lab
visionlab-hz
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 23 hours ago
Scaling Properties of Same-Family On-Policy Distillation upvoted a paper about 23 hours ago
PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy DistillationOrganizations
None yet
upvoted 4
papers about 23 hours ago
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Paper • 2609.36608 • Published • 6
PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation
Paper • 2609.34605 • Published • 5
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Paper • 2608.19669 • Published • 5
