DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 127
KaiyiZhang
Cardlnal
AI & ML interests
None yet
Recent Activity
submitted a paper 1 day ago
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards authored a paper 1 day ago
Interpreting Key Mechanisms of Factual Recall in Transformer-Based
Language Models authored a paper 1 day ago
Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation
of the Reversal CurseOrganizations
None yet