arxiv:2603.15500
minbeomkim
mbkim
·
AI & ML interests
Safe, Reliable, and Controllable AI Agency.
Recent Activity
authored a paper 5 days ago
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty authored a paper about 1 month ago
Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR