Rethink_SFT_generalization
Collection
Repo for paper Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability. • 40 items • Updated • 13
machine not learning
titanwings
·
AI & ML interests
None yet
Recent Activity
upvoted a collection 2 days ago
Rethink_SFT_generalization upvoted a paper 3 days ago
ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent SafetyOrganizations
None yet
upvoted a collection 2 days ago