On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Paper • 2609.35259 • Published • 205
Bas Jansen
basjansen
·
AI & ML interests
Retraining LLMs on my laptop, send help
Recent Activity
upvoted a paper 19 days ago
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics upvoted a paper 19 days ago
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation upvoted a paper 19 days ago
X-Tree: Tokenizing Reusable Experience for Efficient Agent GeneralizationOrganizations
None yet
upvoted 4
papers 19 days ago
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
Paper • 2610.02148 • Published • 23
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Paper • 2609.32993 • Published • 80
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Paper • 2610.00559 • Published • 69
liked a
dataset 19 days ago