🧑🔬 Xiaokang Zhang — papers of 2026 — Elamur Research1 paper · all years of Xiaokang ZhangSparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse RolloutsAnnual Meeting of the Association for Computational Linguistics (ACL)Sijia Luo, Xiaokang Zhang, Yuxuan Hu, et al.2026 · 4 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/xiaokang-zhang/year/2026/