multimodal

Existing surveys predominantly examine isolated components of multimodal pipelines and lack empirically grounded, pedagogically oriented integration frameworks for teaching and learning contexts. Method: This study introduces the first taxonomy and analytical framework covering five core modalities—natural language, video, sensor data, human-centered signals, and environmental logs—and proposes a novel “mid-fusion” paradigm for multimodal data integration. It further innovates by applying citation graph pruning to achieve structured, high-precision literature synthesis. Contribution/Results: Through systematic review, taxonomic modeling, and multimodal fusion design, we demonstrate that multimodal synergy enables detection of fine-grained learning behaviors imperceptible to unimodal analysis. While prediction accuracy remains largely unchanged, interpretability improves significantly, yielding deeper insights into learners’ cognitive-affective states and training outcomes.

This study addresses the challenge that multimodal models struggle to reliably bind textual prompts (e.g., “image”) to their corresponding input modalities, resulting in inadequate source modality tracking. The work formally defines and empirically investigates the “source modality monitoring” problem for the first time, introducing an evaluation paradigm grounded in target-modality information retrieval. By integrating syntactic manipulation with semantic perturbation, the authors systematically assess binding mechanisms across eleven prominent vision-language models. Their findings reveal that semantic cues dominate the binding process when modality distributions exhibit significant divergence, consistently outweighing syntactic signals. These insights offer critical evidence and a novel perspective for enhancing the reliability and robustness of multimodal agents.

Addressing the challenge of scarce target-domain data for complex real-world problems, this paper tackles the limitations of single-domain multimodal data fusion. Method: We propose a novel cross-domain multimodal knowledge fusion paradigm, formally defining the cross-domain multimodal fusion problem for the first time. Our approach introduces a four-layer framework—comprising domain, linkage, model, and data layers—that systematically addresses the core questions of *what to fuse*, *why fusion is feasible*, and *how to fuse*. Key techniques include fusion-aware knowledge graph alignment, cross-domain representation learning, multi-scale feature normalization, and mechanism-driven coupled/decoupled fusion models. Contribution/Results: The method enables end-to-end deployment and significantly enhances generalization and robustness in resource-constrained scenarios, demonstrating state-of-the-art performance on urban anomaly detection and industrial fault diagnosis tasks.

A critical shortage exists of high-quality, large-scale, semantically aligned acoustic–visual–textual multimodal datasets. Method: This paper proposes an end-to-end framework for constructing video-based multimodal data, integrating three key components: (i) video content filtering, (ii) cross-modal synchronization triplet extraction (audio–frame–subtitle), and (iii) fine-grained description synthesis leveraging image-to-text generation models—ensuring temporal and semantic alignment across all three modalities. Contribution/Results: The resulting publicly released dataset spans diverse real-world scenarios and substantially advances performance on cross-modal retrieval and joint embedding learning tasks, achieving state-of-the-art results across multiple benchmarks. By providing a scalable, high-fidelity resource, this work establishes a new foundation for training and evaluating foundational multimodal models.

Traditional multimodal approaches rely on modality-specific encoders and late fusion, limiting scalability and cross-modal generalization. This work proposes a unified paradigm that reformulates diverse multimodal tasks—including text, image, audio, and video processing—as “next-frame prediction,” with all inputs and outputs represented as serialized video frames, enabling end-to-end, single-model inference. It pioneers the task-redefinition strategy—previously confined to NLP—within multimodal learning, eliminating modality-specific design in favor of a fully modality-agnostic architecture. The framework integrates cross-modal tokenization, sequential frame representation, autoregressive modeling, and a shared Transformer decoder, supporting joint multi-task pretraining. Empirical evaluation demonstrates strong zero-shot and few-shot generalization across text-to-text, image-to-text, video-to-video, video-to-text, and audio-to-text tasks. Crucially, adaptation requires only lightweight task-specific heads, underscoring its flexibility and efficiency.

This study addresses the unclear mechanisms underlying cross-layer fusion of visual and textual information in multimodal large language models. We propose an architecture-aware diagnostic framework that systematically compares concatenation-based and native multimodal architectures. Through alignment decoupling, attention entropy analysis, intrinsic dimensionality estimation, causal intervention, and vision-specific Centered Kernel Alignment (CKA), we reveal how feature spaces are reorganized under different architectural paradigms. Our findings indicate that concatenation-based models exhibit a text-dominant fusion trajectory, whereas native models achieve early-stage vision-language co-adaptation. This work elucidates the distinct multimodal fusion mechanisms inherent to these two architectural paradigms, providing a principled theoretical foundation for future model design.

This work addresses the challenge that certain modalities may introduce interference under specific inputs in multimodal fusion, thereby degrading model performance. To mitigate this issue, the authors propose a plug-and-play pre-fusion calibration module that leverages cross-modal summary contrast to extract supportive and conflicting cues, generating instance-level and dimension-level modulation signals. These signals dynamically enhance beneficial features while suppressing misleading information. The method achieves, for the first time, fine-grained, conflict-aware modulation prior to fusion and is compatible with both sequential and convolutional architectures. It consistently improves performance across five benchmark tasks—including emotion understanding and action recognition—and demonstrates enhanced robustness and consistency under modality missingness and data perturbations.

This work systematically investigates the core mechanisms of modality interaction in multimodal pretraining, focusing on knowledge transfer, synergistic effects, and fusion timing. Through experiments on both synthetic and large-scale real-world datasets, it provides the first empirical evidence of asymmetric cross-modal knowledge flow and demonstrates that data complexity governs whether modalities exhibit synergy or competition. The study further validates that early unified fusion consistently outperforms late alignment. Leveraging an architecture featuring shared attention and normalization layers with modality-specific feedforward components, the proposed approach is evaluated on a 13.5B mixture-of-experts model trained on 2 trillion tokens, confirming its effectiveness. Additionally, the paper introduces a highly efficient pretraining strategy that achieves strong generative performance using only 5% of the typical computational budget.

This study addresses the unclear trade-offs among diverse capabilities—such as general visual understanding, structured reasoning, and fine-grained OCR—in multimodal instruction tuning under mixed data regimes, particularly the lack of systematic investigation into how data organization influences these trade-offs. Treating data scheduling as a first-order design variable while holding model architecture and optimization settings fixed, the work compares four strategies: direct mixing, curriculum learning, balanced sampling, and reverse curriculum. Results demonstrate that curriculum-based training—sequencing tasks from general comprehension to specialized skills—achieves superior overall performance and structured reasoning while accelerating convergence. Balanced sampling improves OCR accuracy at the cost of capability imbalance, whereas reverse curriculum degrades performance and induces optimization instability. The findings highlight the critical role of training sequence in shaping the capability distribution of multimodal models.

This work addresses the limitations of existing approaches that predominantly rely on non-native late-fusion architectures and lack a systematic definition or unified framework for native multimodal modeling. The paper proposes a formal roadmap for Native Multimodal Modeling (NMM), introducing, for the first time, a rigorous formulation of “architectural nativeness.” Leveraging an input–output duality perspective, it categorizes models into three types: Multi-to-Text, Multi-to-Target, and Multi-to-Multi. A full-stack, industrial-grade NMM framework is developed, encompassing data governance, early/mid-stage fusion, end-to-end training, and deployment, all realized through a unified Transformer architecture that enables symbiotic cross-modal understanding and generation. This paradigm demonstrates superior performance and strong scalability across multiple tasks, offering a clear pathway toward truly native multimodal models.