Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization Paper • 2610.25973 • Published 19 days ago
Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values Paper • 2605.28170 • Published May 27 • 1
Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values Paper • 2605.28170 • Published May 27 • 1
ToDi: Token-wise Distillation via Fine-Grained Divergence Control Paper • 2505.16297 • Published May 22, 2025 • 3
ToDi: Token-wise Distillation via Fine-Grained Divergence Control Paper • 2505.16297 • Published May 22, 2025 • 3