Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion

• URL: http://arxiv.org/abs/2603.22372v1
• Date: Mon, 23 Mar 2026 07:44:46 GMT
• Title: Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
• Abstract summary: We show that multimodal models with naive fusion strategies often underperform unimodal TS models.<n>We propose constrained fusion methods designed to control such integration.<n>We conduct over 20K experiments across various datasets and TS/text models.
• Score: 12.754011132549167
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting. However, most existing methods provide limited gains, often improving performance only in specific datasets or relying on architecture-specific designs that limit generalization. In this paper, we show that multimodal models with naive fusion strategies (e.g., simple addition or concatenation) often underperform unimodal TS models, which we attribute to the uncontrolled integration of auxiliary modalities which may introduce irrelevant information. Motivated by this observation, we explore various constrained fusion methods designed to control such integration and find that they consistently outperform naive fusion methods. Furthermore, we propose Controlled Fusion Adapter (CFA), a simple plug-in method that enables controlled cross-modal interactions without modifying the TS backbone, integrating only relevant textual information aligned with TS dynamics. CFA employs low-rank adapters to filter irrelevant textual information before fusing it into temporal representations. We conduct over 20K experiments across various datasets and TS/text models, demonstrating the effectiveness of the constrained fusion methods including CFA. Code is publicly available at: https://github.com/seunghan96/cfa/.

Related papers

• Evidence Triangulation for Multimodal Fact-Checking in the Wild [14.259306741814372]
  We introduce X-POSE, a benchmark of real-world, community-annotated multimodal posts from X (formerly Twitter)<n>We also propose TRENT, a novel MFC model that performs evidence triangulation using three parallel cross-attention streams.
  arXiv  Detail & Related papers  (2026-06-30T08:59:12Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach [99.80480649258557]
  DiTFuse is an instruction-driven framework that performs semantics-aware fusion within a single model.<n>Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention.
  arXiv  Detail & Related papers  (2025-12-08T05:04:54Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation [7.627299398469962]
  We propose a new Spectrum-based Modality Representation graph recommender.<n>It aims to capture both uni-modal and fusion preferences while simultaneously suppressing modality noise.<n>Experiments on three real-world datasets show the efficacy of our proposed model.
  arXiv  Detail & Related papers  (2024-12-19T15:53:21Z)
• Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation [61.91492500828508]
  Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal support samples.<n>We introduce a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality.<n>We propose a simple yet effective Test-time Adaptive Cross-modal (TACC) technique to mitigate training bias.
  arXiv  Detail & Related papers  (2024-10-29T19:28:41Z)
• Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition [48.84506301960988]
  Cued Speech (CS) is a pure visual coding method used by hearing-impaired people. automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text.
  arXiv  Detail & Related papers  (2024-01-31T05:20:29Z)
• A Self-Adjusting Fusion Representation Learning Model for Unaligned Text-Audio Sequences [16.38826799727453]
  How to integrate relevant information of each modality to learn fusion representations has been one of the central challenges in multimodal learning. In this paper, a Self-Adjusting Fusion Representation Learning Model is proposed to learn robust crossmodal fusion representations directly from the unaligned text and audio sequences. Experiment results show that our model has significantly improved the performance of all the metrics on the unaligned text-audio sequences.
  arXiv  Detail & Related papers  (2022-11-12T13:05:28Z)
• Attention Bottlenecks for Multimodal Fusion [90.75885715478054]
  Machine perception models are typically modality-specific and optimised for unimodal benchmarks. We introduce a novel transformer based architecture that uses fusion' for modality fusion at multiple layers. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks.
  arXiv  Detail & Related papers  (2021-06-30T22:44:12Z)

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.