June 29, 2026 Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation STCA 将历史自注意力替换为目标-历史交叉注意力，复杂度从 O(L²) 降至 O(L)，RLB 在请求级复用用户编码，实现 10K 长序列端到端训练，已部署于抖音全量流量 long-sequence cross-attention efficient-training industrial-deployment scaling-law