Generative Embeddings with Test-Time Scaling, Toward Efficient Visual Document Retrievers, and More!

Vol.124 for Sep 29 - Oct 05, 2025

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

This week’s newsletter highlights the following research:

1. ModernVBERT: Efficient Visual Document Retrieval via Bidirectional Encoders and Late Interaction, from Teiletche et al.

2. Test-Time Scalable Text Embeddings via Iterative Contrastive Refinement, from National Taiwan University

3. Understanding Scaling Laws in Generative Recommendation Systems, from Snap Inc.

4. Fine-tuning with RAG for Improving LLM Learning of New Skills, from Imperial College London

5. Achieving State-of-the-Art Text Embeddings with 6 Million Open-Source Training Examples, from CodeFuse AI

6. Multi-Agent Deep Search Over Structured and Unstructured Graph Knowledge, from Yang et al.

7. Optimizing LLMs for Reasoning-Intensive Document Retrieval Through Rubric-Based Scoring, from Lan et al.

8. Scalable Deep Research with 4B Parameter Models, from Fractal AI Research

9. Adaptive Patch-Level Embedding Pruning for Storage-Efficient Visual Document Retrieval, from Yan et al.

10. Multilingual Learned Sparse Retrieval Through Lexical Space Alignment, from Nguyen et al.