#multimodal-retrieval News & Analysis

4 articles tagged with #multimodal-retrieval. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Jun 46/10

🧠

Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)

The EReL@MIR 2025 Multimodal Document Retrieval Challenge invited teams to build retrieval systems handling both closed-set document page retrieval and open-domain Wikipedia passage retrieval from text and image queries. The competition attracted 22 teams with 586 submissions, with winning systems favoring decoder-based Multimodal-LLM embedders over traditional CLIP-style encoders.

AINeutralarXiv – CS AI · Jun 16/10

🧠

Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval

Researchers introduce Dynamic Adapter Routing (DAR), a novel approach to continual multimodal retrieval that moves beyond traditional class-incremental learning methods. The study presents a new evaluation framework for vision-language models that better captures real-world retrieval dynamics, with DAR demonstrating superior performance and strong generalization capabilities.

AINeutralarXiv – CS AI · Mar 37/108

🧠

PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval

Researchers introduce PhotoBench, the first benchmark for personalized photo retrieval using authentic personal albums rather than web images. The study reveals critical limitations in current AI systems, including modality gaps in unified embedding models and poor tool orchestration in agentic systems.

AIBullisharXiv – CS AI · Mar 26/1018

🧠

Reason to Contrast: A Cascaded Multimodal Retrieval Framework

Researchers introduce TTE-v2, a new multimodal retrieval framework that achieves state-of-the-art performance by incorporating reasoning steps during retrieval and reranking. The approach demonstrates that scaling based on reasoning tokens rather than model size can significantly improve performance, with TTE-v2-7B reaching 75.7% accuracy on MMEB-V2 benchmark.