On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Paper • 2609.36659 • Published • 87
Shufan Shen
shufanshen
AI & ML interests
Interpretable machine learning, parameter-efficient fine-tuning.
Recent Activity
upvoted a paper 6 days ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training submitted a paper 6 days ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training authored a paper 10 days ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-TrainingOrganizations
upvoted a paper 6 days ago
submitted a
paper to Daily Papers 6 days ago
authored 2
papers 10 days ago
liked 3
models 25 days ago
updated a
collection 27 days ago
published a
dataset 27 days ago