Analyzing Diffusion And Autoregressive Vision Language Models In Multimodal Embedding Space

Abstract

Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation. Recent advances in large foundation models have substantially accelerated the development of embedding models, including those based on Large Language Models (LLMs), Vision Language Models (VLMs), and Multimodal LLMs. More recently, Large Diffusion Language Models (dLLMs) and Multimodal dLLMs have emerged as competitive alternatives to autoregressive models, offering advantages such as bidirectional attention and parallel generation. This progress naturally raises a critical yet unexplored question: can Multimodal dLLMs serve as effective multimodal embedding models? To answer this, we present the first systematic study of converting Multimodal dLLMs into embedding models. We evaluate state-of-the-art Multimodal dLLMs and Autoregressive VLMs across three categories of embedding tasks: classification, visual question answering, and information retrieval. Our resu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2026analyzing

Related papers

• Vlm2vec: Training Vision-language Models For Massive Multimodal Embedding Tasks (2024)0.00
• Indexing Multimodal Language Models For Large-scale Image Retrieval (2026)0.00
• Vlm2vec-v2: Advancing Multimodal Embedding For Videos, Images, And Visual Documents (2025)0.00
• Magic-mm-embedding: Towards Visual-token-efficient Universal Multimodal Embedding With Mllms (2026)0.00
• Generative Giants, Retrieval Weaklings: Why Do Multimodal Large Language Models Fail At Multimodal Retrieval? (2025)0.00
• Unlocking Multimodal Document Intelligence: From Current Triumphs To Future Frontiers Of Visual Document Retrieval (2026)0.00
• WAVE: Learning Unified & Versatile Audio-visual Embeddings With Multimodal LLM (2025)0.00
• Breaking The Modality Barrier: Universal Embedding Learning With Multimodal Llms (2025)4.52