MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval

• URL: http://arxiv.org/abs/2510.15543v1
• Date: Fri, 17 Oct 2025 11:20:35 GMT
• Title: MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
• Authors: Qiyu Wu, Shuyang Cui, Satoshi Hayakawa, Wei-Yao Wang, Hiromi Wakaki, Yuki Mitsufuji,
• Abstract summary: Multimodal large language models (MLLMs) enable a unified encoder that directly processes composed inputs.<n>While flexible and advanced, we identify that unified encoders trained with conventional contrastive learning are prone to learn modality shortcut.<n>We propose a modality composition awareness framework to mitigate this issue.
• Score: 34.21875369884307
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align modality-specific embeddings with contrastive learning, recent multimodal large language models (MLLMs) enable a unified encoder that directly processes composed inputs. While flexible and advanced, we identify that unified encoders trained with conventional contrastive learning are prone to learn modality shortcut, leading to poor robustness under distribution shifts. We propose a modality composition awareness framework to mitigate this issue. Concretely, a preference loss enforces multimodal embeddings to outperform their unimodal counterparts, while a composition regularization objective aligns multimodal embeddings with prototypes composed from its unimodal parts. These objectives explicitly model structural relationships between the composed representation and its unimodal counterparts. Experiments on various benchmarks show gains in out-of-distribution retrieval, highlighting modality composition awareness as a effective principle for robust composed multimodal retrieval when utilizing MLLMs as the unified encoder.

Related papers

• CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension [49.6969505536365]
  We propose CREM, with a unified framework that enhances multimodal representations for retrieval while preserving generative ability.<n>CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T08:09:51Z)
• ReMatch: Boosting Representation through Matching for Multimodal Retrieval [29.610030065465793]
  ReMatch is a framework that leverages the generative strength of MLLMs for multimodal retrieval.<n>We train the embedding MLLM end-to-end with a chat-style generative matching stage.<n>Our experiments show particularly strong zero-shot generalization results on five datasets.
  arXiv  Detail & Related papers  (2025-11-24T16:28:49Z)
• Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation [9.37169920239321]
  Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content.<n>While effective, it remains unclear whether their gains stem from true multimodal understanding or increased model complexity.<n>This work investigates the role of multimodal item embeddings, emphasizing the semantic informativeness of the representations.
  arXiv  Detail & Related papers  (2025-08-06T15:53:58Z)
• NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification [17.10113184019939]
  Multi-modal object Re-Identification (ReID) aims to obtain accurate identity features across heterogeneous modalities.<n>In this paper, we propose a reliable caption generation pipeline based on attribute confidence.<n>We also propose a novel ReID framework, named NEXT, to model diverse identity patterns.
  arXiv  Detail & Related papers  (2025-05-26T13:52:28Z)
• Learning Item Representations Directly from Multimodal Features for Effective Recommendation [51.49251689107541]
  multimodal recommender systems predominantly leverage Bayesian Personalized Ranking (BPR) optimization to learn item representations.<n>We propose a novel model (i.e., LIRDRec) that learns item representations directly from multimodal features to augment recommendation performance.
  arXiv  Detail & Related papers  (2025-05-08T05:42:22Z)
• A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition [3.4568313440884837]
  We present the Anchor-based Multimodal Embedding with Semantic Synchronization (A-MESS) framework.<n>We first design an Anchor-based Multimodal Embedding (A-ME) module that employs an anchor-based embedding fusion mechanism to integrate multimodal inputs.<n>We develop a Semantic Synchronization (SS) strategy with the Triplet Contrastive Learning pipeline, which optimize the process by synchronizing multimodal representation with label descriptions.
  arXiv  Detail & Related papers  (2025-03-25T09:09:30Z)
• Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation [55.99632509895994]
  We introduce LAMIA, a novel approach for multi-aspect semantic tokenization.<n>Unlike RQ-VAE, which uses a single embedding, LAMIA learns an item palette''--a collection of independent and semantically parallel embeddings.<n>Our results demonstrate significant improvements in recommendation accuracy over existing methods.
  arXiv  Detail & Related papers  (2024-09-11T13:49:48Z)
• Fine-tuning Multimodal Large Language Models for Product Bundling [53.01642741096356]
  We introduce Bundle-MLLM, a novel framework that fine-tunes large language models (LLMs) through a hybrid item tokenization approach.<n>Specifically, we integrate textual, media, and relational data into a unified tokenization, introducing a soft separation token to distinguish between textual and non-textual tokens.<n>We propose a progressive optimization strategy that fine-tunes LLMs for disentangled objectives: 1) learning bundle patterns and 2) enhancing multimodal semantic understanding specific to product bundling.
  arXiv  Detail & Related papers  (2024-07-16T13:30:14Z)
• 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)
• Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment [11.897888221717245]
  This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment. Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
  arXiv  Detail & Related papers  (2024-03-11T01:07:36Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)

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.