Introduces kernel contracts framework with derived bounds on divergence from logit drift to reward drift, specialized for RL post-training under support and norm assumptions.
Understanding reinforcement learning for model training, and future directions with grape.arXiv preprint arXiv:2509.04501, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment
Introduces kernel contracts framework with derived bounds on divergence from logit drift to reward drift, specialized for RL post-training under support and norm assumptions.