On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Paper • 2609.35259 • Published • 146
Luca Hoffmann
lhoffmann-ml
·
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
upvoted a paper about 11 hours ago
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics upvoted a paper about 11 hours ago
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents upvoted a paper about 11 hours ago
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic ScenesOrganizations
None yet
upvoted 4
papers about 11 hours ago
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Paper • 2609.32520 • Published • 14
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
Paper • 2610.02117 • Published • 14
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
Paper • 2609.39687 • Published • 13
liked a
dataset about 11 hours ago