Towards AI Search Paradigm, Zero-Shot Mixture of Retrievers, and More!

Vol.110 for Jun 23 - Jun 29, 2025

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

This week’s newsletter highlights the following research:

1. Building Next-Generation Search with Multi-Agent LLM Systems, from Baidu Search

2. Multi-Granularity Retriever Mixing for Robust Information Retrieval, from Kalra et al.

3. Contrastive Item Tokenization for Multi-Modal Generative Recommendation, from Alibaba

4. Self-Supervised Dense Retrieval through Language Modeling, from Cai et al.

5. Nested Embeddings for Scalable E-commerce Information Retrieval, from Qian et al.

6. Entity-Centric Inverted Indexing for Scalable Retrieval-Augmented Generation, from Zhang et al.

7. jina-embeddings-v4: Unified Vision-Language Embeddings with Shared Semantic Space, from Jina AI

8. End-to-End Learning of Search-Augmented Multimodal Reasoning, from ByteDance

9. Hierarchical MLP-Mixer for Multi-Scale User Interest Modeling in Sequential Recommendation, from ByteDance

10. Efficient and Scalable Retrieval Augmented Generation for Dynamic Corpora, from Zhang et al.