RUC-AIBOX · 5 records

dateidtitleauthorsvenue↑
2026-11-202611.26510AutoMaster: Autonomous Post-Training by Making the Same Model a Better TeacherGuoxin Chen et al.arXiv10
2026-10-142610.16533Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable RewardsZhipeng Chen et al.arXiv9
2026-09-172609.14320SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral ReparameterizationZian Liu et al.arXiv13
2026-08-112608.09096Evo-Bench: Can Language Models Improve Agent Harness?Lisheng Huang et al.arXiv18
2026-07-162607.12395Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent ReasoningXinyu Tang et al.arXiv90