Top Information Retrieval Papers of the Week

Top Information Retrieval Papers of the Week

Solving the RAG Inference Bottleneck, An End-to-End Generative Framework for E-commerce Search, and More!

Vol.120 for Sep 01 - Sep 07, 2025

Sumit's avatar
Sumit
Sep 05, 2025
∙ Paid
2
2
Share

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

This week’s newsletter highlights the following research:

  1. An End-to-End Generative Framework for Industrial E-commerce Search, from Kuaishou

  2. A Model-Agnostic System for Customizable Deep Research Agent Deployment, from NVIDIA

  3. A Family of ModernBERT-Based Embedding Models for Enterprise Information Retrieval, from IBM

  4. Leveraging Uncertainty in Unlabeled Data for Improved Recommendations, from Zhao et al.

  5. Multi-Task Learning and Data Synthesis for State-of-the-Art Text Embeddings, from Kingsoft AI

  6. Fine-Grained Scoring and Reinforcement Learning for Efficient Text Reranking, from Alibaba

  7. Addressing Algorithm Adaptation Bias in Recommender System Evaluation, from Roblox

  8. Training LLMs to be Better Text Embedders through Bidirectional Reconstruction, from Su et al.

  9. Solving the RAG Inference Bottleneck with Adaptive Chunk Embeddings, from Meta

  10. Leveraging Code Generation Models for High-Performance Code Embeddings, from Jina AI

Keep reading with a 7-day free trial

Subscribe to Top Information Retrieval Papers of the Week to keep reading this post and get 7 days of free access to the full post archives.

Already a paid subscriber? Sign in
© 2025 Sumit Kumar
Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture