Listwise Generation Raises Short-Video Engagement in Existing Rankers
LIGE-GR adds causal list context, a list-level value function, and RL beam decoding to existing rankers, raising Reels time spent by 1.14%.
Sep 17, 20264 min2609.18148
Information Retrieval
cs.IRIndexing, dictionaries, retrieval, content and analysis.
Sort:
DREAM Improves Taobao Feed Metrics Without Replacing Rankers
An intent engine and agentic meta-control layer steer existing recommendation stages, lifting GMV 1.31% when extended through fine ranking.
Aug 15, 20264 min2608.09408
Request-Level Sharing Cuts Recommendation Inference Cost
ROCS separates request-side and candidate-side computation, reaching up to 3× higher retrieval QPS and 50% higher ranking QPS in production.
Aug 1, 20265 min2607.27744
SlimPer Scales Recommendation Histories Without Quadratic Attention
A compact knowledge-base backbone queries full user histories at each layer, improving offline ranking metrics while cutting per-example FLOPs by 8×–25×.
Jul 28, 20265 min2607.12281
XAlign: Multilingual Retrieval Without Parallel Data
A novel alignment objective maps passages across 100+ languages to a shared space, outperforming prior retrievers by 4-8 points.
May 12, 20247 min2405.06789 Code available