2 papers
stat.ML2026
RLVR is a Kernel, Not a Function: Statistical Inference for pass@ Crossovers
Chen Yang, Xianyang Zhang, Jun Chen
Reinforcement learning with verifiable rewards (RLVR) often improves pass@1 while falling behind its base model at larger sampling budgets , a crossover read as evidence that RL…
cs.IT2026
Learning from Totally Unpaired Data via Minimum Conditional Entropy Coupling
Shahab Asoodeh, Cheuk Ting Li, Jun Chen
Consider an "unsupervised classification" setting, where the goal is to learn a predictor of the categorical class variable using the categorical feature variables $Y_1,\ldots,…