Gated Recursive Fusion: A Stateful Approach to Scalable Multimodal Transformers

• URL: http://arxiv.org/abs/2507.02985v1
• Date: Tue, 01 Jul 2025 09:33:38 GMT
• Title: Gated Recursive Fusion: A Stateful Approach to Scalable Multimodal Transformers
• Authors: Yusuf Shihata,
• Abstract summary: Gated Recurrent Fusion (GRF) is a novel architecture that captures the power of cross-modal attention within a linearly scalable, recurrent pipeline.<n>Our work presents a robust and efficient paradigm for powerful, scalable multimodal representation learning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is prohibitive for settings with many modalities. We address this challenge with Gated Recurrent Fusion (GRF), a novel architecture that captures the power of cross-modal attention within a linearly scalable, recurrent pipeline. Our method processes modalities sequentially, updating an evolving multimodal context vector at each step. The core of our approach is a fusion block built on Transformer Decoder layers that performs symmetric cross-attention, mutually enriching the shared context and the incoming modality. This enriched information is then integrated via a Gated Fusion Unit (GFU) a GRU-inspired mechanism that dynamically arbitrates information flow, enabling the model to selectively retain or discard features. This stateful, recurrent design scales linearly with the number of modalities, O(n), making it ideal for high-modality environments. Experiments on the CMU-MOSI benchmark demonstrate that GRF achieves competitive performance compared to more complex baselines. Visualizations of the embedding space further illustrate that GRF creates structured, class-separable representations through its progressive fusion mechanism. Our work presents a robust and efficient paradigm for powerful, scalable multimodal representation learning.

Related papers

• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [50.438552588818]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution [88.20464308588889]
  We propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR.<n>This method is designed through unfolding an SR optimization function constrained by structural similarity.<n>Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption.
  arXiv  Detail & Related papers  (2025-06-13T14:29:40Z)
• Gated Multimodal Graph Learning for Personalized Recommendation [9.466822984141086]
  Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering.<n>We propose RLMultimodalRec, a lightweight and modular recommendation framework that combines graph-based user modeling with adaptive multimodal item encoding.
  arXiv  Detail & Related papers  (2025-05-30T16:57:17Z)
• Co-AttenDWG: Co-Attentive Dimension-Wise Gating and Expert Fusion for Multi-Modal Offensive Content Detection [0.0]
  We introduce a novel multi-modal Co-AttenDWG architecture that leverages dual-path encoding, co-attention with dimension-wise gating, and advanced expert fusion.<n>We validate our approach on the MIMIC and SemEval Memotion 1.0, where experimental results demonstrate significant improvements in cross-modal alignment and state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-25T07:26:00Z)
• Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions [94.21989689001848]
  We propose (Delta)ConvFusion to replace conventional self-attention modules with Pyramid Convolution Blocks ((Delta)ConvBlocks)<n>By distilling attention patterns into localized convolutional operations while keeping other components frozen, (Delta)ConvFusion achieves performance comparable to transformer-based counterparts while reducing computational cost by 6929$times$ and surpassing LinFusion by 5.42$times$ in efficiency--all without compromising generative fidelity.
  arXiv  Detail & Related papers  (2025-04-30T03:57:28Z)
• M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification [23.322598623627222]
  M$3$amba is a novel end-to-end CLIP-driven Mamba model for multi-modal fusion.<n>We introduce CLIP-driven modality-specific adapters to achieve a comprehensive semantic understanding of different modalities.<n>Experiments have shown that M$3$amba has an average performance improvement of at least 5.98% compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-09T05:06:47Z)
• Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model [18.19558762805031]
  This paper proposes the Coupled SSM model, for coupling state chains of multiple modalities while maintaining independence of intra-modality state processes. Experiments on CMU-EI, CH-SIMS, CH-SIMSV2 through multi-domain input verify the effectiveness of our model. Results demonstrate that Coupled Mamba model is capable of enhanced multi-modal fusion.
  arXiv  Detail & Related papers  (2024-05-28T09:57:03Z)
• GraFT: Gradual Fusion Transformer for Multimodal Re-Identification [0.8999666725996975]
  We introduce the textbfGradual Fusion Transformer (GraFT) for multimodal ReID. GraFT employs learnable fusion tokens that guide self-attention across encoders, adeptly capturing both modality-specific and object-specific features. We demonstrate these enhancements through extensive ablation studies and show that GraFT consistently surpasses established multimodal ReID benchmarks.
  arXiv  Detail & Related papers  (2023-10-25T00:15:40Z)
• Transformer Fusion with Optimal Transport [25.022849817421964]
  Fusion is a technique for merging multiple independently-trained neural networks in order to combine their capabilities. This paper presents a systematic approach for fusing two or more transformer-based networks exploiting Optimal Transport to (soft-)align the various architectural components.
  arXiv  Detail & Related papers  (2023-10-09T13:40:31Z)
• Deep Equilibrium Multimodal Fusion [88.04713412107947]
  Multimodal fusion integrates the complementary information present in multiple modalities and has gained much attention recently. We propose a novel deep equilibrium (DEQ) method towards multimodal fusion via seeking a fixed point of the dynamic multimodal fusion process. Experiments on BRCA, MM-IMDB, CMU-MOSI, SUN RGB-D, and VQA-v2 demonstrate the superiority of our DEQ fusion.
  arXiv  Detail & Related papers  (2023-06-29T03:02:20Z)
• MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid [40.745848169903105]
  Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs. MMEA algorithms rely on KG-level modality fusion strategies for multi-modal entity representation. This paper introduces MEAformer, a multi-modal entity alignment transformer approach for meta modality hybrid.
  arXiv  Detail & Related papers  (2022-12-29T20:49:58Z)
• Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion [112.27103169303184]
  Multimodal Knowledge Graphs (MKGs) organize visual-text factual knowledge. MKGformer can obtain SOTA performance on four datasets of multimodal link prediction, multimodal RE, and multimodal NER.
  arXiv  Detail & Related papers  (2022-05-04T23:40:04Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)

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.