203 citations · 224 across the 17 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures
Hamed Mahdavi, Pouria Mahdavinia, Majid Farhadi +1
Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify the derivation behind it, a…
cs.LG2026
PAC-Bayes Beyond Parameter Space: Behavioral Equivalence, Z-Information, and Exact Complexity Decomposition
Vasant G. Honavar, Satish Kumar Keshri, Neil Ashtekar +1
PAC-Bayes theory provides generalization guarantees by controlling the Kullback--Leibler (KL) divergence between posterior and prior distributions over a chosen hypothesis represen…