2 papers
cs.LG2026
Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning
Ziyue Wang, Aomufei Yuan, Yongfu Zhu +10
Reinforcement Learning from Verifiable Rewards (RLVR) has become the dominant approach for improving mathematical reasoning in large language models, yet current methods reduce eac…
cs.CR2025
Neural-Inspired Advances in Integral Cryptanalysis
Liu Zhang, Yiran Yao, Danping Shi +3
The study by Gohr et.al at CRYPTO 2019 and sunsequent related works have shown that neural networks can uncover previously unused features, offering novel insights into cryptanalys…