CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension

• URL: http://arxiv.org/abs/2602.19091v1
• Date: Sun, 22 Feb 2026 08:09:51 GMT
• Title: CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension
• Authors: Lihao Liu, Yan Wang, Biao Yang, Da Li, Jiangxia Cao, Yuxiao Luo, Xiang Chen, Xiangyu Wu, Wei Yuan, Fan Yang, Guiguang Ding, Tingting Gao, Guorui Zhou,
• Abstract summary: 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.
• Score: 49.6969505536365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains challenging due to the discrepancy between output formats and optimization objectives. Previous approaches often employ contrastive fine-tuning to adapt MLLMs for retrieval, but at the cost of losing their generative capabilities. We argue that both generative and embedding tasks fundamentally rely on shared cognitive mechanisms, specifically cross-modal representation alignment and contextual comprehension. To this end, we propose CREM (Compression-driven Representation Enhanced Model), with a unified framework that enhances multimodal representations for retrieval while preserving generative ability. Specifically, we introduce a compression-based prompt design with learnable chorus tokens to aggregate multimodal semantics and a compression-driven training strategy that integrates contrastive and generative objectives through compression-aware attention. Extensive experiments demonstrate that CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks. Our findings highlight that generative supervision can further improve the representational quality of MLLMs under the proposed compression-driven paradigm.

Related papers

• Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models [67.45032003041399]
  We propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs.<n>MPCO adaptively balances the importance of different paradigm representations and guides the global optimisation.<n>Our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2026-03-05T06:01:26Z)
• Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality [59.651410243721045]
  CoCoA is a Content reconstruction pre-training paradigm based on Collaborative Attention for multimodal embedding optimization.<n>We introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding EOS> embeddings.<n>Experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality.
  arXiv  Detail & Related papers  (2026-03-02T05:34:45Z)
• Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval [25.629529312687694]
  We propose Reasoning Guided Embeddings (RGE), which preserves the generative rationale process of Multimodal Large Language Models (MLLMs)<n>Our method first enables the model to perform structured rationale generation conditioned on the instruction, and then extracts representations after reasoning has unfolded.<n>Experiments on the MMEB benchmark show that reasoning-guided conditioning improves multimodal retrieval performance by 4.9% over the non-reasoning baseline.
  arXiv  Detail & Related papers  (2025-11-20T08:44:47Z)
• Compression then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding [53.18433310890516]
  Vision-language models advance multimodal representation learning by acquiring transferable semantic embeddings.<n>We propose CoMa, a compressed pre-training phase, which serves as a warm-up stage for contrastive learning.
  arXiv  Detail & Related papers  (2025-11-11T17:23:02Z)
• MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval [34.21875369884307]
  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.
  arXiv  Detail & Related papers  (2025-10-17T11:20:35Z)
• Growing Visual Generative Capacity for Pre-Trained MLLMs [60.826355079902505]
  Bridge is a pure autoregressive unified MLLM that augments pre-trained visual understanding models with generative ability.<n>We propose a semantic-to-pixel discrete representation that integrates compact semantic tokens with fine-grained pixel tokens.
  arXiv  Detail & Related papers  (2025-10-02T00:40:02Z)
• CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning [24.981279071712173]
  We introduce CAFe, a contrastive-autoregressive fine-tuning framework that enhances LVLMs for both representation and generative tasks.<n>Our approach unifies these traditionally separate tasks, achieving state-of-the-art results in both multimodal retrieval and multimodal generative benchmarks.
  arXiv  Detail & Related papers  (2025-03-25T17:57:17Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [89.50068130832635]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation MLLMs by multimodal knowledge.<n>We propose Chain-of-Description for step-by-step visual understanding and integrate structured Chain-of-Thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Experiments demonstrate SIcog's effectiveness in developing MLLMs with enhanced multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• LFTR: Learning-Free Token Reduction for Multimodal Large Language Models [3.368594680297987]
  We introduce a learning-free token reduction (LFTR) method designed for Multimodal Large Language Models (MLLMs)<n>By capitalizing on the redundancy in visual representations, our approach effectively reduces tokens while preserving the general inference performance of MLLMs.<n>Our results show that LFTR achieves up to a $16times$ reduction of visual tokens while maintaining or even enhancing performance on mainstream vision question-answering benchmarks.
  arXiv  Detail & Related papers  (2025-01-29T02:52:32Z)
• Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints [15.541287957548771]
  We propose a Coarse-to-fine Consistency Constraints Visual Grounding architecture.<n>It integrates implicit and explicit modeling approaches within a two-stage framework.<n>It significantly outperforms state-of-the-art REC and RIS methods by a substantial margin.
  arXiv  Detail & Related papers  (2025-01-12T04:30:13Z)
• Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor [4.35807211471107]
  This work proposes a novel two-stage consistency learning approach for retrieved information compression in retrieval-augmented language models. The proposed method is empirically validated across multiple datasets, demonstrating notable enhancements in precision and efficiency for question-answering tasks.
  arXiv  Detail & Related papers  (2024-06-04T12:43:23Z)
• 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.