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

This week’s newsletter highlights the following research:

1. Production-Scale LLM Ranking for Semantic Search, from LinkedIn

2. The Role of Embedding Magnitude in Contrastive Learning, from NAIST

3. Bidirectional Diffusion Models for Dense Text Embeddings, from Perplexity AI

4. Exposing Reproducibility Failures and Conceptual Flaws in Diffusion Recommenders, from Benigni et al.

5. Learning Sparse High-Dimensional Embeddings for Efficient Collaborative Filtering, from Vančura et al.

6. LLM-Driven Autonomous Optimization for Industrial-Scale Recommendation Systems, from Google

7. Compressing User Histories into Learnable Memory for Scalable Generative Recommendation, from Tencent

8. Scaling Industrial Ranking Models to 15 Billion Parameters with TokenMixer-Large, from ByteDance

9. A Reasoning-Enhanced LLM Framework for Recommendation Re-ranking, from Meta

10. Establishing Scaling Laws for Massive-Scale Recommender Systems, from Meta