Paper Archive
论文 主线

输入关键词搜索 120 项内容

tracked author

Jianwei Zhang

Recurring Qwen author across Qwen2.5, Qwen3 and Bebop. OpenReview records an Alibaba Group researcher profile with confirmed alibaba-inc.com email and Google Scholar link. No high-confidence personal X account was found.

3 archived notes X: not-found

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档

On the Design of Qwen3.8 Next Architecture: Evaluation, Efficiency, and Training Stability

Qwen3.8 Flash Next 将三层 Gated DeltaNet 与一层 Qwen Sparse Attention 交错，并用四分支门控残差、可卸载的 N gram Embedding 和重新拟合的 Muon 训练配方共同降低训练与长上下文推理成本；125B 主模型每个 token 激活约 6B 参数，在十四项预训练评测中有八项超过 397B A17B 的 Qwen3.7 Plus Base，同时使用约三分之一的训练 token 和约九分之一的训练 FLOPs，但报告没有披露完整数据账本、端到端服务测量或多随机种子复验。

待审阅 2026-08-26-qwen3-8-flash-next-architecture Sparse AttentionLinear AttentionTraining Stability