Bridging the Gap Between Text-Only and Multimodal Retrieval, The Case for Corpus Expansion in RAG and More!

Vol.125 for Oct 06 - Oct 12, 2025

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

This week’s newsletter highlights the following research:

1. A 3B Parameter Unified Embedding Model for Cross-Modal Retrieval Across Text, Image, Audio, and Video, from NVIDIA

2. Exploiting Attention Sparsity for Efficient In-Context Document Ranking, from Google DeepMind

3. Corpus Scaling as a Substitute for Model Scaling in Retrieval-Augmented Generation, from CMU

4. A Framework for Adapting Pre-trained Language Models to Industrial-Scale Generative Recommendation, from YouTube

5. Embedding Generation via Chain-of-Thought in Large Language Models, from CUHK

6. Controlled Analysis of Context Length Effects on LLM Performance Under Perfect Retrieval Conditions, from Du et al.

7. A Think-Then-Embed Framework for Multimodal Retrieval, from Meta

8. A Model-Agnostic Approach to Long-Tail Item Recommendation Through Strategic Sampling, from Alshabanah et al.

9. A Deployable Search Agent Framework for Knowledge-Intensive Question Answering, from Alibaba

10. Decoupling Search and Reasoning in Language Model Agents, from Wang et al.