Understanding Embedding Scaling in Collaborative Filtering, Domain Knowledge Acquisition for LLMs via RL, and More!

Vol.123 for Sep 22 - Sep 28, 2025

Stay Ahead of the Curve with the Latest Advancements and Discoveries in Information Retrieval.

This week’s newsletter highlights the following research:

1. Scalable Multimodal Retrieval Through Flexible Late Interaction and Test-Time Budget Control, from Meta

2. How Interaction Noise Shapes Embedding Scalability in Collaborative Filtering Models, from He et al.

3. Embedding Domain Expertise in LLMs through Reinforcement Learning from Augmented Generation, from Nie et al.

4. EmbeddingGemma: Powerful and Lightweight Text Representations, from Google DeepMind

5. Bringing Context Engineering and Reasoning to Industrial Cascade Ranking Systems, from Shopee

6. The Role of Vocabularies in Learning Sparse Representations for Ranking, from Naver

7. Improving Dual Encoders for Multi-Level Document Retrieval, from Google DeepMind

8. A Production-Ready Generative Framework for Unified Search and Recommendation, from Alibaba

9. A Unified PyTorch Framework for Large-Scale Sparse-Dense Recommendation Training, from Alibaba

10. Treating Reranking as Noise Reduction in Multi-Stage Recommender Systems, from Kuaishou