MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model

• URL: http://arxiv.org/abs/2602.06393v1
• Date: Fri, 06 Feb 2026 05:18:33 GMT
• Title: MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
• Authors: Geonmo Gu, Byeongho Heo, Jaemyung Yu, Jaehui Hwang, Taekyung Kim, Sangmin Lee, HeeJae Jun, Yoohoon Kang, Sangdoo Yun, Dongyoon Han,
• Abstract summary: Multi-Turn Contrastive Learning (MuCo) is a dialogue-inspired framework that revisits this process.<n>Experiments exhibit MuCo with a newly curated 5M multimodal multi-turn dataset (M3T)
• Score: 57.89395815934156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its empirical success, they are primarily built on a "single-turn" formulation where each query-target pair is treated as an independent data point. This paradigm leads to computational inefficiency when scaling, as it requires a separate forward pass for each pair and overlooks potential contextual relationships between multiple queries that can relate to the same context. In this work, we introduce Multi-Turn Contrastive Learning (MuCo), a dialogue-inspired framework that revisits this process. MuCo leverages the conversational nature of MLLMs to process multiple, related query-target pairs associated with a single image within a single forward pass. This allows us to extract a set of multiple query and target embeddings simultaneously, conditioned on a shared context representation, amplifying the effective batch size and overall training efficiency. Experiments exhibit MuCo with a newly curated 5M multimodal multi-turn dataset (M3T), which yields state-of-the-art retrieval performance on MMEB and M-BEIR benchmarks, while markedly enhancing both training efficiency and representation coherence across modalities. Code and M3T are available at https://github.com/naver-ai/muco

Related papers

• UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark [72.37370242707432]
  This paper introduces the UniM benchmark, the first Unified Any-to-Any Interleaved Multimodal dataset.<n>UniM contains 31K high-quality instances across 30 domains and 7 representative modalities.<n>We also introduce the UniM Evaluation Suite, which assesses models along three dimensions: Semantic Correctness & Generation Quality, Response Structure Integrity, and Interleaved Coherence.
  arXiv  Detail & Related papers  (2026-03-05T11:45:16Z)
• Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective [42.832839189236694]
  We propose MAMMQA, a multi-agent QA framework for multimodal inputs spanning text, tables, and images.<n>Our system includes two Visual Language Model (VLM) agents and one text-based Large Language Model (LLM) agent.<n> Experiments on diverse multimodal QA benchmarks demonstrate that our cooperative, multi-agent framework consistently outperforms existing baselines in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-05-27T07:23:38Z)
• What to align in multimodal contrastive learning? [7.7439394183358745]
  We introduce Contrastive MultiModal learning strategy that enables the communication between modalities in a single multimodal space.<n>Our theoretical analysis shows that shared, synergistic and unique terms of information naturally emerge from this formulation.<n>In the latter, CoMM learns complex multimodal interactions and achieves state-of-the-art results on the seven multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-09-11T16:42:22Z)
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation [63.31007867379312]
  We introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantics. We employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets.
  arXiv  Detail & Related papers  (2024-05-24T08:58:48Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• LLMBind: A Unified Modality-Task Integration Framework [38.95771765322677]
  We introduce textbfLLMBind, a novel framework designed to unify a diverse array of multi-modal tasks. By harnessing a Mixture-of-Experts (MoE) Large Language Model (LLM), LLMBind processes multi-modal inputs and generates task-specific tokens, enabling the invocation of corresponding models to accomplish tasks.
  arXiv  Detail & Related papers  (2024-02-22T12:36:31Z)
• AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling [115.56746545958522]
  We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities.<n>We build a multimodal text-centric dataset for multimodal alignment pre-training.<n>We show that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities.
  arXiv  Detail & Related papers  (2024-02-19T15:33:10Z)
• Toward Robust Multimodal Learning using Multimodal Foundational Models [30.755818450393637]
  We propose TRML, Toward Robust Multimodal Learning using Multimodal Foundational Models. TRML employs generated virtual modalities to replace missing modalities. We also design a semantic matching learning module to align semantic spaces generated and missing modalities.
  arXiv  Detail & Related papers  (2024-01-20T04:46:43Z)
• Multi-modal Contrastive Representation Learning for Entity Alignment [57.92705405276161]
  Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs. We propose MCLEA, a Multi-modal Contrastive Learning based Entity Alignment model. In particular, MCLEA firstly learns multiple individual representations from multiple modalities, and then performs contrastive learning to jointly model intra-modal and inter-modal interactions.
  arXiv  Detail & Related papers  (2022-09-02T08:59:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.