How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
Paper • 2604.25907 • Published • 2
Chu-Cheng Lin
kitsing-goog
·
AI & ML interests
None yet
Recent Activity
submitted a paper about 19 hours ago
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum authored a paper 7 days ago
Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to DataOrganizations
submitted a
paper to Daily Papers about 19 hours ago
authored a
paper 7 days ago