IR Papers Weekly Vol.169: Netflix builds LLM-native ranker, Yandex replaces 15+ models with one generative recommender
_reachsumit · x · 2026-08-16
This week's IR papers (Vol.169) highlight: Netflix's GenRec replacing production ranker with LLM trained on natural language; Yandex's single generative recommender replacing 15+ models; plus research on retrieval-augmented reasoning, memory allocation, RAG evaluation, and generative embedding models.
More from Research
- Seminal Paper: Legibility vs. Predictability in Robot Motion — tomssilver · 2026-08-17
- Paper: ResearchArena evaluates sabotage and monitoring in automated AI R&D — maksym_andr · 2026-08-17
- AI agents fail in companies due to missing "hippocampus" memory — thebvg · 2026-08-17
- Deep Dive into Transformer and LLM Architecture for Non-STEM Readers — Zulfikar_Ramzan · 2026-08-17
- UniProbe reduces VLM hallucinations by 55% with minimal latency overhead — HaggaiMaron · 2026-08-17
- Zvi Proposes Generalizing AI Constitution Definitions — TheZvi · 2026-08-17