Multimodal Fusion

Current multimodal fusion approaches, particularly those based on static Mixture-of-Experts (MoE) architectures, often struggle to provide the adaptive and efficient collaborative reasoning required by complex real-world applications. We introduce the Dynamic Agent-based Interaction Network (DAIN), which reconceptualizes multimodal fusion as a dynamic, multi-agent collaborative process. DAIN employs a context-aware Meta-Controller that dynamically schedules sparse activation of specialized interaction agents and orchestrates compressed inter-agent communication for consensus-building. The framework is guided by a multi-objective loss function that jointly optimizes task accuracy, agent specialization, and operational efficiency through sparse activation and communication regularization. Comprehensive evaluations across five diverse benchmarks -- ADNI, MIMIC-IV, MM-IMDB, CMU-MOSI, and ENRICO -- establish DAIN as a new state-of-the-art, delivering significant performance improvements including a 2.6% accuracy gain on ADNI. Ablation studies verify the critical roles of both dynamic scheduling and agent communication. Furthermore, DAIN offers enhanced interpretability by exposing context-dependent agent roles and collaboration patterns while maintaining computational efficiency through sample-wise sparse agent activation. Our work demonstrates the promise of dynamic, agent-based paradigms for multimodal reasoning.

Multimodal feature fusion can effectively capture complex patterns in real-world data by integrating complementary information from different modalities. However, in many applications, such as boiler combustion monitoring, equipment failure, inconsistent sensor sampling frequencies, and network delays often cause missing modalities and temporal asynchrony. These issues lead to incomplete and disorderly multimodal data. To address them, previous studies have proposed several data fusion methods that align cluster centers before fusion. However, these methods have two key limitations. First, they cannot guarantee accurate sample-level alignment of data pairs. Second, they do not address significant discrepancies in data sizes across different classes, which may affect subsequent fusion performance. To address these problems, we propose a dual-learning based penalized multi-align clustering model, named DLPMAC. The dual-learning mechanism enables the model to learn prior knowledge from each modality, including semantic and structural information. This helps preserve semantic consistency and structural similarity across modalities at both local and global levels. In addition, the penalized multi-align module performs multi-to-multi data alignment through a penalty mechanism. It allows one sample to form data pairs with different samples from other modalities, thereby improving data-pair alignment accuracy. The penalty mechanism also prevents data aggregation, avoiding the case where excessive samples are linked to a single sample. Experimental results demonstrate the effectiveness of DLPMAC in addressing data alignment and fusion challenges from both sampling and clustering perspectives.

Recent advances in Human Activity Recognition (HAR) from wearable sensors have shown that multi-modal deep learning models consistently outperform their uni-modal counterparts. Modalities can include IMUs, RGB cameras, audio signals, and others. One important aspect of multi-modal deep learning is the sensor fusion approach we apply. Over recent years, multiple fusion paradigms have been proposed for multi-modal HAR. However, to the best of our knowledge, no head-to-head comparison of these paradigms exists on a common multi-modal HAR benchmark dataset. To address this research gap, we systematically compare seven state-of-the-art sensor fusion methods on the recently released HARMES dataset, which comprises 61 hours of fully labeled IMU, audio, and ambient humidity data. The chosen dataset focuses on 15 household and personal hygiene activities of daily living (ADLs). By applying the seven different fusion techniques to a state-of-the-art multi-modal model architecture, we show that Gated Multi-modal Fusion achieves the highest macro F1-score (0.82), surpassing the concatenation-based late fusion HARMES paper baseline of 0.76 by +6pp under leave-one-participant-out evaluation. All code used in our experiments is made publicly available on GitHub.

Many multimodal systems estimate the reliability of each modality and weight their contributions to the final prediction. However, it remains unclear whether these scores influence model decisions or merely correlate with performance. We propose a simple diagnostic to test whether reliability information is used during inference. After training, the model and inputs are fixed while reliability scores are permuted across test examples. If predictions depend on these scores, performance should degrade. Experiments on StressID for stress recognition and CMU-MOSEI for sentiment analysis show that permuting reliability scores leaves performance unchanged despite substantial potential gains from selecting the best modality per example. In positive controls where reliability signals identify the correct modality, the same frozen fusion rules yield significant improvements, indicating that reliability signals influence fused decisions only when they reliably predict unimodal correctness.

RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors. While this multi-modal scheme broadens tracking applicability, real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion. In harsh environments, either modality can lose reliability drastically, and targets frequently appear incomplete due to occlusion, edge truncation and foreground clutter.To tackle the above challenges, we present a hierarchical perturbation and retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation, termed APRTrack. To mimic real-world signal corruption, APRTrack constructs structured degradation via two adversarial perturbation branches at the modality and spatial levels, which separately simulate full-modal failure and localized target region absence. A hierarchical routing mechanism is designed to disentangle the training pipelines of the two perturbation types, effectively eliminating feature collapse induced by superimposed degradation constraints. Furthermore, we devise Footprint-guided Channel-calibrated Hopfield Retrieval (FCHR) for reliable historical information compensation. This module evaluates retrieval confidence based on association footprints between queries and memory banks, and calibrates the retrieval metric space prior to Hopfield matching, realizing controllable historical feature compensation bounded to target regions. Extensive experiments on FE108, COESOT, VisEvent, and FELT datasets demonstrate the effectiveness of our proposed strategies for the RGB-Event visual object tracking. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenEvTracking

Micro-expression recognition (MER) is challenging due to subtle facial movements, limited data, and the ambiguous relationship between Action Units (AUs) and emotion categories. Optical flow and motion magnification are two widely used representations for making subtle facial dynamics observable. However, many existing methods treat them as separate cues or fuse them without explicitly modeling their dual complementarity. Optical flow encodes displacement-level muscle motion, whereas motion magnification reveals appearance-level changes in facial texture and context. When both modalities are informative, their combination provides a more complete characterization of subtle facial dynamics; when one modality degrades, the other may still preserve discriminative evidence for compensation. This dual complementarity provides richer facial representations, but also introduces two key challenges for multimodal fusion: cross-modal heterogeneity and spatially varying modality reliability. To address these challenges, we propose SAC$^2$-Net, a Semantic Anchoring and Complementary-Consensus Network that first aligns heterogeneous visual representations with semantic anchors and then performs reliability-aware complementary fusion. Specifically, Semantic Anchoring Soft Alignment (SASA) converts activated AUs into textual prompts and uses hierarchical AU-aware soft labels to align motion-magnified and optical-flow representations while preserving semantic proximity among anatomically related samples. Based on the aligned representations, Complementary-Consensus Fusion (CCF) exchanges complementary motion and appearance cues, adaptively enhances unreliable local responses with trustworthy cross-modal evidence, and further encourages a shared spatial focus through consensus refinement.

Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely on auxiliary input signals or suffer from costly computational expense. To efficaciously enhance the segmentation performance without introducing intolerable costs, we propose to transfer the rich knowledge from the multi-modal model (i.e., point clouds and images) and multiple model experts to the point-cloudbased network through knowledge distillation. Specifically, we present Information-oriented Heterogeneous Distillation (IHD) to help the uni-modal model absorb the complementary knowledge from the multi-modal teacher. We design the Information-Oriented Filtering (IOF) strategy to select informative images from the continuous image sequence for multi-modal fusion. This practice can boost the performance of the multi-modal teacher, thus benefiting the learning of the student. Besides, as opposed to vanilla model ensembling that requires the separate training of each expert, we propose Adept Snapshot Distillation (ASD). ASD treats the freely available model snapshots generated during the training phase as multiple experts, which significantly reduces the training cost for model ensembling. For each expert teacher, it only provides supervision to the student in the class where it is adept. The resulting Heterogeneous and Adept Snapshot Knowledge Distillation, dubbed HAS-KD, attains state-of-the-art results on ScanNetV2 and S3DIS datasets. HAS-KD can be seamlessly integrated into contemporary 3D segmentation algorithms and bring considerable gains without introducing extra inference burdens. The code will be made publicly available upon publication.

Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous regions. Current segmentation models handle this in one of two inadequate ways: deterministic fusion that averages away disagreement, or post-hoc uncertainty estimation decoupled from the fusion process that produces it. Both obscure the clinically critical question: why is this prediction unreliable? We present EnTrust, a framework that treats inter-modal conflict as the primary source of predictive uncertainty. Our EnFuse module decomposes multimodal features into three disentangled components: shared anatomical consensus (F_c), modality-specific cues (F_{u,m}), and spatially localized conflict signals (F_{cf}), with independence enforced via a cross-covariance objective. This structured decomposition conditions SegDiff, a diffusion-based generative segmentation model whose sampled hypotheses diverge specifically in regions of modal disagreement. TrustMap then translates this hypothesis divergence into calibrated, pixel-wise uncertainty using ensemble entropy, conflict-guided perturbation probing, and a learned calibration head, enabling clinicians to understand not only where predictions are uncertain, but why. Across four benchmarks spanning brain, cardiac, lesion, and oncology domains, EnTrust achieves state-of-the-art segmentation accuracy while reducing calibration error by 40% compared to the strongest baseline. Notably, it outperforms 5x deep ensembles using a single model at roughly half the memory footprint. Code and checkpoints are available at https://github.com/GenMI-Lab/EnTrust.git.

Automated skin cancer classification from dermoscopic images remains challenging due to heterogeneous lesion structure, strong intra-class variability, and subtle visual differences between benign and malignant cases. Existing CNN/ViT pipelines typically rely on global or patch-level features and often combine patient metadata via late fusion, which limits spatially grounded multimodal reasoning. We present a novel region-based graph learning framework that explicitly models lesions as graphs of spatially coherent superpixel regions represented as frozen CNN features. To capture fine-grained lesion arrangements, we encode inter-regional geometry as edge attributes and introduce a dedicated metadata context node connected to all regions, providing structured integration of demographic/clinical variables within the same relational space. Node representations are updated using our edge-aware graph transformer followed by attention-driven propagation, and a final graph-level embedding for benign-malignant classification. Experiments on four public benchmarks demonstrate that explicit region-level relational modeling and graph-native multimodal fusion yield consistent gains over the state-of-the-art. Consequently, we establish a new graph-centric perspective in which CNN features are modeled as relational nodes and improved through contextual integration, yielding more expressive and robust classifications.

Recent multimodal survival prediction models have demonstrated strong predictive performance by leveraging complementary information across modalities. However, such models generally assume data completeness and exhibit limited robustness toward missing modalities, which are frequently encountered in real-world clinical settings. We propose the Evidential Missing Modality Survival Fusion (EMMS) model for multimodal survival prediction under missing modalities. EMMS offers a straightforward, computationally effective approach to survival analysis without requiring a generative phase for missing data. By employing Dempster-Shafer theory and Gaussian Random Fuzzy Numbers for multimodal decision fusion, it considers both aleatoric and epistemic uncertainty alongside modality reliability for fusion. Moreover, the model treats missing modalities as vacuous evidence, preventing interference with available inputs and naturally reflecting increased uncertainty and calibrated predictions. Extensive experiments on four cancer datasets demonstrate state-of-the-art performance while providing calibrated and interpretable uncertainty estimates under incomplete multimodal observations, without introducing additional computational overhead.

This paper presents Vortex, the multimodal video retrieval system developed by our team, FocusOnFun, for the Ho Chi Minh City AI Challenge 2025, designed to advance intelligent multimedia search and temporal reasoning. The system integrates adaptive keyframe extraction, multimodal metadata generation from vision-language and speech models, and a hybrid retrieval strategy that fuses CLIP and SigLIP2 embeddings through Reciprocal Rank Fusion to balance global and fine-grained semantics. To enhance interactivity, Vortex incorporates Rocchio-based relevance feedback and a multi-stage temporal search mechanism for sequential event alignment. Built on Milvus and Elasticsearch, the architecture enables scalable indexing and efficient retrieval. Evaluated in the official competition, our FocusOnFun team's system achieved a score of 79.6/88 (90.5%) in the Preliminary Round and was further evaluated in the Final Round, achieving an Excellent' overall performance with Outstanding' results in the question-answering (QA) task. This demonstrating the complementary strengths of CLIP and SigLIP2 and confirming the effectiveness of the hybrid retrieval approach. The system establishes a robust foundation for future research in intelligent, context-aware, and interactive video retrieval.

Feature misalignment in BEV perception is a critical yet often overlooked challenge in autonomous driving, especially under calibration uncertainties between LiDAR and camera sensors. To address this issue, we propose a robust multi-modal fusion framework, GraphBEV++, which systematically mitigates projection-induced misalignment. The framework consists of two key modules: LocalAlign-v2 and GlobalAlign-v2. LocalAlign-v2 introduces neighborhood-aware depth features via graph matching to correct local misalignment. It supports both LSS-based and query-based BEV representations, making it compatible with BEVFusion and BEVFormer architectures for consistent cross-paradigm alignment. GlobalAlign-v2 encompasses two variants: Deformable and Diffusion. The Deformable variant addresses global misalignment in LSS-based multi-modal BEV by explicitly learning cross-modal feature offsets. In contrast, the Diffusion variant targets implicit misalignment in query-based BEV by injecting noise to simulate misalignment and employing a denoising process to recover aligned features. Experimental results show that GraphBEV++ achieves state-of-the-art performance under misalignment noise on nuScenes and Waymo subset, improves long-range detection on Argoverse2, and generalizes effectively to the 3D occupancy prediction task, consistently improving occupancy estimation accuracy and robustness under both clean and noisy settings. Furthermore, GraphBEV++ effectively alleviates misalignment issues in end-to-end autonomous driving. Compared with five baselines (UniAD, VAD, FusionAD, MomAD, and WoTE), it demonstrates superior performance in both open-loop (nuScenes) and closed-loop (Bench2Drive and NAVSIM) evaluations across perception, prediction, and planning tasks.

Timely and accurate disaster damage assessment is crucial for effective emergency response, resource allocation, and recovery. Traditional methods, which often rely on manual inspections or sparse data, are typically slow and error-prone. This paper introduces a novel framework leveraging remote sensing imagery and deep learning to automate building damage classification. Using pre- and post-disaster satellite imagery, our model categorizes buildings into four damage levels: no damage, minor damage, major damage, and destroyed. The core innovation is a multi-modal attention mechanism that fuses bi-temporal features to explicitly detect and assess structural changes. We employ a lightweight ConvNeXT-Tiny backbone to ensure efficient processing without compromising performance. Key contributions include: (1) a cross-attention module for multi-modal data fusion, (2) an optimized preprocessing pipeline for large-scale datasets, and (3) robust data augmentation techniques. Experiments on a large-scale disaster dataset demonstrate an overall classification accuracy of 94.90%. The model effectively discriminates between damage categories and remains resilient to incomplete data. This system significantly improves assessment speed and accuracy, aiding emergency responders in prioritizing interventions. This work advances automated disaster damage detection by integrating multi-temporal imagery with deep learning, offering a scalable solution for real-time response.

Diffusion-based style transfer must balance inference efficiency with stylization fidelity. Adapter-based methods are efficient, but they inject style as an external condition and can either weaken reference-specific appearance or copy reference semantics into the generated image. Optimization-based personalization methods such as LoRA internalize style more effectively, but require a separate training process for every new style. We introduce i2L (image-to-LoRA), a framework that amortizes style LoRA training into a single forward pass. Given one or more reference images, i2L predicts LoRA weights for a text-to-image model, enabling immediate style instantiation without per-style optimization. The architecture combines an image encoder, learnable LoRA queries, and compressed decoding heads that generate adapted matrices. Training on semantically diverse style pairs encourages the predictor to preserve appearance cues while suppressing reference-content copying. Experiments on Z-Image, FLUX.2, and Hidream-O1 show that i2L improves style fidelity, prompt alignment, and perceptual quality over existing baselines. Because i2L produces explicit LoRA weights, it also supports asymmetric classifier-free guidance, multi-reference style fusion, and composition with controllable-generation modules.

We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made. We propose Latent World Recovery (LWR), a framework built on two key ideas: (i) modality-specific embeddings from different modalities are aligned in a shared latent space, and (ii) a unified representation is constructed by fusing only the embeddings of the modalities that are actually available at both training and inference time. Rather than imputing missing modalities or requiring a fixed modality set, LWR treats each modality as a partial perception of an underlying latent state and performs availability-aware representation learning directly from the observed modalities. This combination of neighbor-based latent alignment and availability-aware modality fusion enables robust multimodal prediction under partial observation, while avoiding error propagation from explicit reconstruction of missing modalities. We evaluate the proposed framework on real-world incomplete multi-omics benchmarks and demonstrate that it provides an effective approach to downstream tasks such as cancer phenotype classification and survival prediction.

Personality assessment aims to infer stable personality traits from dynamic behaviors across language, voice, and facial cues. Since different personality dimensions are revealed through distinct behavioral perspectives, modeling trait-specific evidence is challenging. However, most existing approaches adopt a uniform multimodal fusion strategy across all dimensions, assuming identical modality contributions. This overlooks trait-specific modality preferences and introduces cross-modal interference. To address this issue, we propose a novel personality assessment framework called Traits Run Deeper, which consists of three components. Specifically, the Multimodal Foundation Representation (MFR) module constructs personality-oriented multimodal inputs and leverages psychology-informed semantic templates as anchors, enabling foundation models to capture trait-relevant information. Building upon MFR, the Trait-Specific Modality Fusion (TSMF) module acts as an asymmetric fusion mechanism, allowing each dimension to selectively exploit different modality pathways from modality-specific modeling to complementary fusion. Thus, TSMF captures heterogeneous modality preferences while reducing cross-modal contamination. Furthermore, the Distribution-Calibrated Personality Regression (DCPR) module mitigates label imbalance and central tendency bias through target distribution calibration, improving robustness and stability. Experimental results on the AVI Challenge 2026 validation set demonstrate the effectiveness of the proposed framework, reducing mean squared error (MSE) by approximately 25% compared with the baseline. Consistent improvements are observed on the official test set, where our method achieves the best performance and ranks first in the Personality Assessment Track. The source code will be made available at https://github.com/MSA-LMC/AVI2026.

Synthetic aperture radar (SAR)-assisted optical cloud removal aims to recover surface information obscured by clouds in optical remote sensing images by exploiting complementary SAR observations. Existing multimodal fusion methods typically rely on direct spatial concatenation and pixel-wise supervision, which can propagate SAR speckle noise into optical reconstruction and lead to over-smoothed results. To address these limitations, we propose an Information Bottleneck-driven High-Fidelity Network (IB-HFN) for SAR-assisted optical cloud removal. IB-HFN employs a dual-stream backbone to preserve modality-specific representations before deep semantic fusion, thereby mitigating premature cross-modal contamination. At the fusion stage, we introduce a Spatial Information Bottleneck Fusion module that compresses SAR features through a channel-wise variational information bottleneck to suppress unstructured speckle noise. In parallel, a local-global gating mechanism predicts clear-sky regions and routes reliable optical details through a Dirac-initialized skip connection, decoupling noise suppression from texture preservation. We further develop a joint optimization strategy that integrates feature-level bottleneck regularization with image-level constraints on reconstruction accuracy, structural consistency, spectral fidelity, and contrastive sharpness. A dynamic weighting schedule balances these objectives to stabilize training and reduce hazy artifacts. Experiments on the SEN12MS-CR dataset under challenging spatio-temporal splits demonstrate that IB-HFN achieves superior structural preservation and spectral fidelity over existing methods.

Multimodal 3D object detection based on LiDAR and cameras has demonstrated excellent performance in ground-vehicle scenarios, but has not been explored for Unmanned Aerial Vehicle (UAV) platforms. In UAV top-down scenes, frequent groundobject occlusion dominated by tree canopies causes spatially varying and modality-dependent information degradation. Existing multimodal fusion frameworks neither explicitly model such ground-object occlusion nor embed occlusion awareness into the detection pipeline, limiting their performance in occluded UAV scenes. To address these challenges, we propose CAMF-Det, a closure-aware multimodal fusion framework for LiDAR-camera 3D object detection on UAV platforms, which derives dual-modal occlusion intensity through physics-inspired modeling and embeds them as priors throughout the detection pipeline. First, a dual-modal closure modeling module explicitly constructs occlusion intensity ground truth for both modalities offline via a Beer-Lambert-inspired formulation and building-mask correction. Second, using these ground-truth maps as supervision, a dual-modal prediction network converts the offline modeling results into online occlusion intensity predictions under single-frame inference. Third, both ground-truth and predicted occlusion intensity are injected into data augmentation, feature encoding, multimodal fusion, and detection head, enabling adaptive detection under spatially varying and modality-dependent information degradation. Experiments on two self-built UAV-based multimodal datasets, SI3D-DI and SI3D-DII, demonstrate that CAMF-Det achieves the best performance across all difficulty levels, with hard-level mAP$_{\mathrm{BEV}}$ improvements of 9.43% and 4.88% over the best competing methods, respectively. These results confirm the effectiveness of explicit occlusion prior modeling and exploitation for robust multimodal 3D detection in UAV scenes.

In healthcare, multimodal time series tasks often operate on incomplete observations in practice, for example when ECG segments are lost because electrodes detach or an entire respiratory channel is unavailable during overnight monitoring. Such missingness typically appears in two structurally distinct patterns: within-modality missing, where values are absent within an otherwise observed modality, and modality-level missing, where an entire modality is unavailable. Existing methods typically represent unobserved data implicitly through masks or missing embeddings, without learning instance-specific missing information, and most are designed for only one missingness pattern. A natural approach is to explicitly estimate the missing data; however, existing imputation methods treat missingness uniformly despite their different structural priors, and the imputation process is often isolated from downstream tasks, preventing downstream tasks from guiding imputation toward more informative representations. To address these limitations, we present PAMF, a multimodal time-series framework that explicitly handles different missingness patterns while coupling imputation with downstream prediction through prior-aware flow matching and weight sharing. Specifically, the method initializes the flow-matching source state with type-specific priors to distinguish two missing types. It further connects imputation and classification through architecturally matched encoders with weight sharing, transferring task-relevant representations into the imputation process. Experiments on multiple multimodal healthcare time-series benchmarks show that the proposed method achieves the strongest overall downstream performance across diverse datasets and missing settings compared with existing baselines.

Ultra-short-term solar irradiance prediction is critical for photovoltaic system dispatch and power grid stability. Existing approaches suffer from three key shortcomings: single time-series models cannot capture the spatial dynamics of clouds under complex conditions, standard convolutions inadequately represent multi-scale cloud features, and fixed low-frequency compensation strategies fail to adapt to different prediction steps. To address these issues, this proposes a multi-source data fusion model for ultra-short-term irradiance prediction. The model first employs InceptionNeXt to extract multi-scale, multi-directional spatial features from ground-based cloud images. A step-adaptive low-frequency compensation unit is then introduced to dynamically modulate global low-frequency information based on the prediction step. Eventually, the enhanced image features are combined with meteorological time-series features, and a TempAttnLSTM network captures global temporal dependencies for multi-step prediction. Experiments on the public NREL dataset and practical photovoltaic stations in Shandong illustrate the effectiveness of the proposed method compared with several state-of-the-art approaches.

Deepfake videos are increasingly challenging the credibility of online content. Many existing detection methodology relies on complex, resource-intensive models, which limit their practical use. The study introduces the ExpSpeech-Net deepfake detection (SqN-R-DFD) model, which utilizes SqueezeNet and RNN (Recurrent Neural Network) as its backbone, providing a lightweight and efficient deepfake detection framework that simultaneously analyzes facial expressions and speech patterns. The approach incorporates advanced feature extraction, such as ISLBT-based features for image and MPNCC for signals, along with a smart feature-selection strategy using SASMA (Sandpiper-Assisted Slime Mould Algorithm), ensuring optimal and balanced input to the detection models. By combining SqueezeNet and an RNN, subtle inconsistencies in deepfake videos are captured effectively. The framework achieves 94.5% accuracy, precision of 99.3%, and F-measure of 96.8%, outperforming conventional methods. This demonstrates that integrating multiple modalities with intelligent preprocessing and feature selection enables practical, real-time deepfake detection suitable for everyday applications.

Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality that is useful for one input may become distracting for another, and local feature responses within the same modality can disagree with evidence from other sources. This work investigates how to adjust multimodal representations before they are merged by a downstream predictor. We develop a compact calibration module that compares each modality with the others at the summary level, extracts cues of cross-source support and conflict, and converts these cues into instance-wise and dimension-wise modulation signals. The calibration is applied to the original modality features rather than to already fused representations, enabling the model to suppress misleading components, preserve weak but useful evidence, and emphasize responses that are better supported by the current multimodal context. The module is designed as a plug-in component and can be attached to different fusion backbones without changing their prediction heads. Across five benchmarks covering sentiment understanding, action recognition, audio-visual event detection, and audio-visual emotion classification, the proposed pre-combination calibration strategy improves performance under both sequence-based and convolutional fusion settings. Additional analyses under modality removal, synthetic corruption, training dynamics, and feature-level visualization show that calibrating signals before fusion can reduce interference from unreliable modalities and produce more stable multimodal optimization.

Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patterns, thereby enhancing data processing and decision-making. While existing methods for structured multimodal inputs are typically designed around specific tasks and assume fully observed modalities, real-world applications often suffer from uncertain or missing modality inputs due to various factors. Some traditional models overly emphasize local interactions within missing modalities, neglecting the global complementary cues embedded in multimodal representations. To overcome these limitations, we propose a Dynamic Multimodal Data Fusion model based on Contrastive Learning (CL-DMDF). CL-DMDF introduces a novel attention mechanism that operates across both feature and modality dimensions to compute reliable attention scores, effectively reflecting importance at each level. The CL-DMDF further incorporates an entity-centroid contrastive learning module that constructs centroid-based positive samples from entity features to enhance discriminative learning. Additionally, an adaptive fusion module is employed to improve the efficiency and accuracy of dynamic fusion strategies. Extensive experiments conducted on three datasets demonstrate the effectiveness of the CL-DMDF across diverse multimodal fusion tasks.

Video-language models are pivotal for tasks such as moment retrieval and highlight detection, yet they often struggle to capture the dynamic, non-linear interactions between temporal video sequences and textual semantics. Existing approaches, relying on static cross-attention or prompt-tuning mechanisms, fail to adaptively model the evolving relationships between modalities, leading to suboptimal alignment and limited generalization. Inspired by systems biology, we propose \textbf{Reaction-Diffusion Multimodal Fusion (RDMF)}, a novel framework that reimagines video-language alignment as a reaction-diffusion (RD) process, drawing on the principles of pattern formation introduced by Alan Turing. In RDMF, video features diffuse across time to capture temporal context, while text-video interactions are modeled as non-linear reactions that amplify relevant features and suppress noise, forming emergent patterns akin to biological systems. Leveraging the Gray-Scott RD model, we design a computationally efficient fusion module that integrates video and text representations, supported by rigorous mathematical analysis of stability and convergence using Turing instability criteria. Our framework is theoretically grounded, employing advanced mathematical tools to ensure stable pattern formation, and is practically viable, incorporating standard components like pretrained encoders and DETR-style heads for moment retrieval and saliency prediction. RDMF represents a pioneering interdisciplinary approach, bridging systems biology and multimedia research to address the limitations of conventional multimodal fusion. Preliminary experiments demonstrate its potential to outperform existing methods in identifying salient video moments, offering a new paradigm for video-language tasks.

Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations. We propose \textit{NeuroAlign}, a hierarchical framework for structured multimodal fusion. It introduces (1) \textit{Dual-Modal Hierarchical Alignment} (DMHA), which models multi-scale dynamic connectivity and aligns dynamic-static and functional-structural embeddings; and (2) \textit{Dual-Domain Hierarchical Interaction} (DDHI), which enables fine-grained modulation and global interaction between connectivity- and region-level features. To support feature-level inspection, we design \textit{Synergistic Activation Mapping} (SAM), a gradient-free, marker-oriented attribution method for DFC, SFC, ALFF, and FA. Evaluated on GUTCM, ADNI, and OASIS under five-fold validation, NeuroAlign achieves competitive MCI/SCD detection and preliminary cross-dataset transferability. Attribution analyses reveal modality-specific and partially consistent brain patterns, providing model-derived evidence for multimodal representation analysis.

The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding. In this paper, we demonstrate that feature alignment quality, not data scale alone, is the primary determinant of which fusion strategy excels. Through controlled experiments on Flickr8k using two feature extraction backbones (ResNet18 and CLIP ViT-B/32), we show that concatenation outperforms cross-attention by 4.1-5.1 percentage points across all tested scales (2048-16384 samples) when features are pre-aligned by a vision-language pretraining objective. We provide a theoretical explanation grounded in sample complexity analysis: concatenation requires O(d_v + d_t) samples to learn its fusion projection, while cross-attention requires O(d_v * d_t) samples to learn bilinear attention weights, over 256 times as many for 512-dimensional CLIP features. When features are already aligned, the approximation error gap between the two methods vanishes, and concatenation's sample efficiency dominates at all practical dataset sizes. An alignment degradation study confirms a monotonic trend: as feature alignment degrades, concatenation's advantage grows from 1.3% to 2.8%. These findings provide a principled decision framework for fusion method selection in multimodal systems, with direct implications for the design of Multimodal Large Language Models.

Real-world multimodal systems must be robust against low-quality data, such as sensor noise, incomplete multimodal data and conflicting inputs. However, existing trustworthy fusion methods rely on the model's own prediction confidence to judge data quality. This creates a circular dependency: when a model is confident but wrong, these methods fail to detect the error. To break this loop, we propose Geometry-based Multimodal Fusion (GMF). Instead of relying on predictions, we evaluate reliability by measuring how much transport correction the input needs in latent space. We implement Diffusion Schrödinger Bridge transport with Rectified Flow, where the squared initial velocity gives an efficient learned correction score. Valid data has low squared velocity magnitude, while noisy, incomplete data or conflicting data requires stronger transport correction. This geometry-based reliability signal acts as an independent judge, effectively flagging unreliable inputs even when the classifier is fooled. Extensive experiments demonstrate that GMF significantly improves robustness against severe sensor noise and semantic conflicts compared to confidence-based baselines.

Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consistent visual representations over time. In this work, we propose a cross-modal architecture that combines RGB video and temporal hand skeleton data within a unified Mamba-based framework, exploiting the linear time complexity of State Space Models (SSMs). Our architecture consists of three components: a VideoMamba module for visual feature extraction, a skeleton encoder built on a stack of Mamba blocks, and a fusion module that integrates both modalities into a single representation. A central contribution of this work is the design and evaluation of four Class (CLS) token mixing strategies for multimodal fusion: Naive, Average, Weighted and Context-based. These strategies differ in how the pretrained unimodal CLS tokens, which role is to act as information sinks concentrating learned representations, are leveraged to initialize the mixed CLS token used for final classification. We evaluate all strategies on the H2O dataset. Experimental results show that the Average strategy achieves the best performance, yielding gains of over 10% Top-1 accuracy in the Tiny configuration and 2% in the Small configuration over the VideoMamba baseline.

State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional sequence modeling capabilities. However, their application to vision tasks remains challenging. First, existing vision SSMs largely depend on manually designed fixed scanning methods to flatten image patches into sequences, which imposes predefined geometric structures and increases the complexity. Second, the broader adoption of vision SSMs is hindered in domains that require query-based interactions between distinct information streams. This is a result of the inherently causal and self-referential nature of SSMs designed for 1D sequence modeling tasks. This fusion mechanism is indispensable for critical perception tasks such as multi-view 3D fusion. To address these limitations, we propose Deformba, a context adaptive method that dynamically augments the spatial structural information while maintaining the linear complexity of SSMs. Deformba also allows multi-modal fusion like cross attention. To demonstrate the effectiveness and general applicability of Deformba, we test its performance on general 2D vision tasks such as image classification, object detection, and segmentation, as well as 3D vision tasks like BEV perception. Extensive experiments show that Deformba achieves strong performance across various visual perception benchmarks.

Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-generated short-form videos have rarely been studied. This paper presents USV, the User-generated Short-form Video dataset for high-level semantic video understanding. The dataset contains around 224K videos collected from UGC platforms by label queries without extra manual verification and trimming. Although video understanding has achieved plausible improvement these years, most works focus on instance-level recognition, which is not sufficient for learning the representation of the high-level semantic information of videos. Therefore, we further establish two tasks: topic recognition and video-text retrieval on USV. We propose two unified and effective baseline methods Multi-Modality Fusion Network (MMF-Net) and Video-Text Contrastive Learning (VTCL), to tackle the topic recognition task and video-text retrieval respectively, and carry out comprehensive benchmarks to facilitate future research. Our project page is https://usvdataset.github.io.

Tactile sensing is a fundamental modality for embodied intelligence, offering unique and direct feedback on contact geometry, material properties, and interaction dynamics that remote sensors cannot replace. However, unimodal tactile perception is inherently limited by its sparse spatial coverage and lack of global semantic context. With the recent explosion in deep learning and large language models, integrating tactile with vision and language has become essential to bridge physical interaction with semantic reasoning, leading to the emergence of Multimodal Tactile Fusion. Despite rapid progress, the existing researches remain fragmented across disparate datasets, sensing modalities, and tasks, lacking a unified theoretical framework. To address this gap, this paper provides a comprehensive survey of multimodal tactile fusion research up to the first quarter of 2026. We propose a hierarchical taxonomy that organizes the field into two primary dimensions: multimodal datasets and multimodal methods. On the data side, we categorize resources ranging from Tactile-Vision datasets, Tactile-Language datasets, Tactile-Vision-Language datasets, and Tactile-Vision-Other datasets. On the method side, we structure prior work into three core pillars: (1) Multimodal Perception and Recognition, which focuses on object understanding and grasp prediction; (2) Cross-Modal Generation, focusing on bidirectional translation between tactile, vision, and text; and (3) Multimodal Interaction, emphasizing feedback control and language-guided manipulation. Furthermore, we summarize representative tactile sensing hardware, review commonly used evaluation metrics and benchmark settings, and discuss current challenges and promising future directions.

Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis by integrating diverse data sources. However, accurate prognosis for ischemic stroke remains challenging due to limitations in existing multi-modal approaches. First, current methods are predominantly confined to dual-modal fusion, lacking a framework that effectively integrates the trifecta of medical images, structured clinical data, and unstructured text. Second, they often fail to establish deep bidirectional interactions between modalities; To address these critical gaps, this paper proposes a novel tri-modal fusion model for ischemic stroke prognosis. Our approach first enriches the data representation by employing a Large Language Model (LLM) to automatically generate semi-structured diagnostic text from brain MRIs. This process not only addresses the scarcity of expert annotations but also serves as a regularized semantic enhancement, improving multimodal fusion robustness. Furthermore, we design a core component termed the Vision-Conditioned Dual Alignment Fusion Module (VDAFM), which strategically uses visual features as a conditional prior to guide fine-grained interaction with the generated text. This module achieves a dynamic and profound fusion through a dual semantic alignment loss, effectively mitigating modal heterogeneity. Extensive experiments on a real-world clinical dataset demonstrate that our model achieves state-of-the-art performance.

Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modality missing, where an entire channel is absent, and within-modality missing, where a contiguous time segment is lost. No existing benchmark evaluates multiple fusion architectures under both failure modes at controlled severity levels across diverse clinical datasets. We present MuteBench, a benchmark covering 9 datasets from 7 clinical domains, 6 fusion architectures, and 2 missing-data modes over 125,000 samples. Through this benchmark, we find that architecture family is the strongest predictor of robustness, outweighing parameter count. Channel-independent models tolerate modality missing well but can be sensitive to within-modality missing, especially on short sequences. Curriculum modality dropout protects reliably only up to the maximum dropout rate used in training. We also find that channel count, sequence length, and modality alignment jointly determine which failure mode poses the greater threat. Finally, a PTB-XL case study suggests that diffusion-based imputation can improve downstream classification under within-modality missing, with the largest gains for models whose expert routing is most sensitive to corrupted inputs, though broader validation across datasets remains an open direction. MuteBench provides practitioners with concrete guidance for both selecting existing architectures and informing the design of future robust multimodal fusion methods.

We present NERVE (Neuromorphic Vision and Radar Ensemble), a multi-sensor dataset comprising 257 minutes of synchronized recordings from five sensors: two Dynamic Vision Sensors (DVS), an RGB-D camera, and two Radar units (24GHz and 77GHz). Captured across 12 measurement days in office environments, NERVE contains around 600GB of uncompressed temporally aligned data with around 914,000 frames and around 9.6 million RGB COCO-formatted annotations covering 16 relevant object categories. To evaluate multi-modal fusion, we construct a DVS+Radar subset for human detection and distance estimation. Baseline experiments using feed-forward and recurrent detectors show that combining DVS with 77GHz Radar consistently improves detection, with recurrent models achieving up to 47.5% mAP and mean absolute Radar distance errors below 1.8m against LiDAR ground truth.

Automated driving has made remarkable progress, yet situations still arise where human intervention is necessary. Teleoperation provides a scalable solution to address such cases, enabling remote operators to support vehicles without being physically present. In this context, video transmission forms the operator's primary source of situational awareness, making video quality a decisive factor for both safety and task performance. In an online study, participants rated compressed video sequences from the Zenseact Dataset and provided subjective quality ratings. These ratings were then used to retrain the Video Multi-Method Assessment Fusion (VMAF) model, yielding an adapted variant tailored to teleoperation. The retrained model demonstrated improved alignment with human ratings compared to the original 4K VMAF. In particular, RMSE decreased from 10.36 to 8.83, and MAD from 8.71 to 6.38, corresponding to improvements of 15% and 27%, respectively. These results highlight that incorporating domain-specific data can enhance the predictive power of established quality metrics in safety-critical applications. At the same time, Outlier cases emerged in which videos received high objective scores despite noticeable degradations in regions critical for the driving task.

Pertussis booster vaccination produces immune responses that vary widely across individuals in both peak magnitude and long-term durability. These two phases are governed by partly distinct biological compartments:peak reflects acute B-cell activation and antibody secretion, while durability reflects the establishment of long-term humoral memory. Yet most computational models target only one, missing the full boost-and-wane trajectory. Jointly predicting both is non-trivial because the two endpoints are biologically dissociated rather than redundant; samples are small, modalities are heterogeneous with structured missingness, and the two tasks rely on different measurement windows. We propose a multi-task contrastive multimodal fusion architecture combining frozen TabPFN-v2 per-modality encoders, a dual-label supervised contrastive loss that treats two subjects as a positive pair if they agree on the Task 1 label or the Task 2 label, modality dropout calibrated to empirical missingness, and missingness-masked attention fusion. Applied to a curated subset of the CMI-PB pertussis booster dataset (n = 158 subjects, four modalities, 44.9% with at least one modality missing; Spearman r = -0.58 between peak and durability, n = 96), the model achieves test AUROC 0.797 (95% CI [0.621, 0.948]) for peak response and 0.755 (95% CI [0.519, 0.945]) for durability, with both significant under joint label permutation (N = 1000; p = 0.002 and p = 0.045). Across logistic regression, XGBoost, and MLP baselines on raw features and on TabPFN embeddings, the proposed model is the only one whose 95% CIs lie above chance on both tasks simultaneously. Per-modality contribution analyses recover task-specific modality contributions consistent with the underlying immunology: peak prediction is carried by cytokine signatures, while durability is carried by baseline antibody features.

The proliferation of sophisticated image editing tools and generative artificial intelligence models has made verifying the authenticity of digital images increasingly challenging, with important implications for journalism, forensic analysis, and public trust. Although numerous forensic algorithms, ranging from handcrafted methods to deep learning-based detectors, have been developed for manipulation detection, individual methods often suffer from limited robustness, fragmented evidence, or weak generalization across manipulation types and image conditions. To address these limitations, we present \textbf{FRAME}, a method for \textbf{F}orensic \textbf{R}outing and \textbf{A}daptive \textbf{M}ulti-path \textbf{E}vidence fusion for image manipulation detection. FRAME organizes diverse forensic algorithms into a multi-path analysis space, adaptively selects informative forensic paths for each input image, and fuses complementary evidence to improve detection and localization performance. By moving beyond single-method analysis and fixed fusion strategies, FRAME provides a more robust and flexible approach to image forensic reasoning while preserving interpretable forensic cues from multiple evidence sources. Experimental results demonstrate the effectiveness of FRAME across diverse manipulation scenarios. Code is available at \href{https://github.com/kzhao5/FRAME}{https://github.com/kzhao5/FRAME}.

Multimodal sensor fusion has demonstrated remarkable performance improvements over unimodal approaches in 3D object detection for autonomous vehicles. Typically, existing methods transform multimodal data from independent sensors, such as camera and LiDAR, into a unified bird's-eye view (BEV) representation for fusion. Although effective in ideal conditions, this strategy suffers from substantial performance deterioration when camera or LiDAR data are missing, corrupted, or noisy. To address this vulnerability, we develop a framework-agnostic fusion module for camera and LiDAR data that allows for handling cases when one of the two modalities is missing or corrupted. To demonstrate the effectiveness of our module, we instantiate it in BEVFusion [1], a well-established framework to combine camera and LiDAR data for 3D object detection. By means of quantitative experiments on the MultiCorrupt dataset, we demonstrate that our module achieves favorable performance improvements under scenarios of missing and corrupted modalities, substantially outperforming existing unified representation approaches across a wide range of sensor deterioration scenarios and reaching state-of-the-art performance in scenarios of corrupted modality due to extreme weather conditions and sensor failure.

The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex remote sensing (RS) scenes, existing studies have predominantly concentrated on architectural optimizations for integrating textual semantic information with visual features, while largely neglecting the generation of high-quality RS captions and the investigation of their effectiveness in multimodal semantic fusion.In this context, we propose the Dynamic MLLM Mixture-of-Experts Perception-Guided Remote Sensing Scene Segmentation, referred to as MPerS.We design multiple prompts for MLLMs to generate high-quality RS captions, enabling MLLMs to perceive RS scenes from diverse expert perspectives. DINOv3 is employed to extract dense visual representations of land-covers.We design a Dynamic MixExperts module that adaptively integrates the most effective textual semantics. Linguistic Query Guided Attention is constructed to utilize textual semantic information to guide visual features for precise segmentation. The MLLMs include LLaVA, ChatGPT, and Qwen. Our method achieves superior performance on three public semantic segmentation RS datasets.

Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision force feedback and control. Although recent efforts have attempted to integrate force/torque sensing into policies, how to build a simple yet effective framework that achieves robust generalization under multimodal observations remains an open question. In this paper, we propose ForceFlow, a force-aware reactive framework built upon flow matching. For contact-stage policy design, we investigate force signal fusion mechanisms and adopt an asymmetric multimodal fusion architecture that treats force as a global regulatory signal, combined with a joint prediction paradigm that enhances the policy's understanding of instantaneous force and historical information, thereby achieving deep coupling between force and motion. For task-level hierarchical decomposition, we divide manipulation into a vision-dominant approach stage (VLM-based pointing for target localization) and a touch-dominant interaction stage (force-driven contact execution), with a Vision-to-Force (V2F) handover mechanism that explicitly decouples spatial generalization from contact regulation. Experimental results across six real-world contact-rich tasks demonstrate that ForceFlow achieves a 37% success rate improvement over the strong baseline ForceVLA while maintaining significantly lower cost. Moreover, ForceFlow exhibits accurate force signal prediction and demonstrates superior performance in contact force self-regulation and zero-shot out-of-distribution (OOD) generalization.

Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they are largely restricted to single-modal inputs and cannot fully exploit complementary information from diverse data sources. In this work, we introduce a new framework for long-tailed recognition that explicitly handles multi-modal inputs. Our approach extends multi-expert architectures to the multi-modal setting by fusing heterogeneous data into a unified representation while leveraging modality-specific networks to estimate the informativeness of each modality. These confidence-guided weights dynamically modulate the fusion process, ensuring that more informative modalities contribute more strongly to the final decision. To further enhance performance, we design specialized training and test procedures that accommodate diverse modality combinations, including images and tabular data. Extensive experiments on benchmark and real-world datasets demonstrate that the proposed approach not only effectively integrates multi-modal information but also outperforms existing methods in handling long-tailed, class-imbalanced scenarios, highlighting its robustness and generalization capability.

Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated learning offers a privacy-respecting framework, but is brittle when clients differ in sensor modality and resolution, when their data distributions drift, and when privacy noise destroys the structural signal needed for localization. We propose UMEDA, a graph federated learning framework in which clients form nodes of a global graph that share a continuous integral operator, and aggregation is reformulated as spectral signal processing on this operator. Each client encodes its local sensors with a linear-attention layer whose kernel spectrum is low-rank filtered, suppressing modality-specific residuals so clients with different sensors align in a common low-rank subspace. The server then aggregates client updates via a diffusion model over the kernel's spectral coefficients, treating updates as discretizations of a shared operator rather than topology-bound weights -- this absorbs varying graph sizes and missing modalities without node-wise correspondence. To balance privacy and utility, we add an anisotropic differential-privacy mechanism that projects noise preferentially into the null space of the signal subspace, preserving dominant eigendirections while ensuring formal $(ε, δ)$-DP under gradient clipping. On MM-Fi and the RELI11D out-of-distribution benchmark, UMEDA outperforms state-of-the-art federated baselines in accuracy, convergence, and communication efficiency, particularly under high modality heterogeneity and tight privacy budgets.

Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structural changes. Consequently, jointly capturing 2D semantic changes and 3D height changes is essential for urban morphology analysis and emergency management. In practical scenarios, collecting 3D observations is often constrained by high acquisition costs and the inability to support frequent updates. The multi-temporal cross-modal input consisting of pre-event Digital Surface Model (DSM) and post-event imagery provides a practical solution for 3D change detection in high-frequency urban monitoring, disaster assessment, and emergency response scenarios. However, this setting remains challenging as imagery and DSM data exhibit significant spectral-geometric representation gaps. Moreover, modality differences may be confused with actual changes, and robust change detection requires effective fusion of semantic and geometric features from multi-temporal data. In this paper, we propose DPG-CD, a depth-prior-guided multi-temporal cross-modal fusion framework for joint 2D semantic and 3D height change detection. Specifically, an estimated depth prior is introduced into the imagery to mitigate the modality gap with DSM. A gated fusion mechanism then selectively injects geometric cues from depth prior while preserving discriminative spectral representations. Subsequently, a multi-stage cross-temporal cross-modal feature fusion architecture is employed to extract change-aware features. Finally, a multi-task decoder jointly predicts 2D semantic changes and 3D height changes, complemented by an auxiliary DSM prediction task to improve structural consistency and height estimation accuracy. Experiments on two public datasets, Hi-BCD and 3DCD, and a new dataset, NYC-MMCD, demonstrate that DPG-CD outperforms state-of-the-art methods on both 2D and 3D change detection tasks.

Infrared-Visible image fusion (IVIF) aims to integrate thermal information and detailed spatial structures into a single fused image to enhance perception. However, existing evaluation approaches tend to over-optimize both hand-crafted no-reference statistics and full-reference metrics that treat the source images as pseudo ground truths. Recent IVIF reward-modelling efforts learn from human ratings but use scalar regression on aggregated scores, neither leveraging the reasoning of Multimodal Large Language Models (MLLMs) nor encoding per-image perceptual ambiguity in their supervision, but naively introducing MLLMs with discrete one-hot supervision likewise collapses fused images of similar quality into different rating levels. To address this, we introduce FuScore, which utilizes an MLLM to mimic human visual perception by producing continuous quality score, rather than discrete level predictions, enabling fine-grained discrimination among fused images of similar quality. We exploit the agreement among four IVIF-specific sub-dimensions to construct a per-image soft label whose sharpness reflects how consensual the overall judgment is. We further introduce a tripartite objective combining per-image distributional supervision, within-source-pair Thurstone fidelity for method-level ordering, and cross-source-pair Thurstone fidelity for scene-level ordering across scenes. Extensive experiments demonstrate that FuScore achieves state-of-the-art correlation with human visual preferences.

Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate models for each modality or rely on pretrained models to adapt to new modalities, which limits efficiency, scalability, and usability. Thus, we introduce OneTrackerV2, a unified multi-modal tracking framework that enables end-to-end training for any modality. We propose Meta Merger to embed multi-modal information into a unified space, allowing flexible modality fusion and robustness. We further introduce Dual Mixture-of-Experts (DMoE): T-MoE models spatio-temporal relations for tracking, while M-MoE embeds multi-modal knowledge, disentangling cross-modal dependencies and reducing feature conflicts. With a shared architecture, unified parameters, and a single end-to-end training, OneTrackerV2 achieves state-of-the-art performance across five RGB and RGB+X tracking tasks and 12 benchmarks, while maintaining high inference efficiency. Notably, even after model compression, OneTrackerV2 retains strong performance. Moreover, OneTrackerV2 demonstrates remarkable robustness under modality-missing scenarios.

Accurate badminton stroke prediction is crucial for fine-grained sports analysis and tactical decision support. However, existing methods struggle to model rich temporal context. This paper introduces TemPose-TF-ASF (Adjacent-Stroke Fusion), a context-aware extension of TemPose. It enhances stroke recognition by incorporating stroke-type information from both preceding and subsequent strokes. A two-stage training and inference strategy is adopted. Preliminary predictions from the baseline model are reused as estimated temporal context. These predictions guide the joint optimization of the ASF module and the classifier. By explicitly modeling bidirectional temporal stroke dependencies, the proposed method can be seamlessly integrated into existing state-of-the-art models. Experiments on a large-scale badminton match dataset show consistent improvements over the baseline and its variants in terms of Accuracy and Macro-F1. Moreover, integrating ASF into other advanced methods yields notable performance gains. These results demonstrate strong transferability and generalization capability.

Scene-text image captioning requires fusing three information streams -- visual features, OCR-detected text, and linguistic knowledge -- to generate descriptions that faithfully integrate text visible in images. Existing fusion approaches treat text as language-agnostic, which fails for Vietnamese: a tonal language where diacritics alter word meaning, OCR errors are pervasive, and word boundaries are ambiguous. We argue that Vietnamese scene-text captioning demands \textit{linguistically informed multimodal fusion}, where language-specific structural knowledge is explicitly incorporated into the fusion mechanism. Motivated from these insights, we propose \textbf{HSTFG} (Heterogeneous Scene-Text Fusion Graph), a general-purpose graph fusion framework with learned spatial attention bias, and show through topology analysis that cross-modal graph edges are harmful for scene-text fusion. Building on this finding, we design \textbf{PhonoSTFG} (Phonological Scene-Text Fusion Graph) which specializes graph-level fusion for Vietnamese linguistic reasoning. To support evaluation, we introduce \textbf{ViTextCaps}, the first large-scale Vietnamese scene-text captioning dataset (\textbf{15{,}729} images with \textbf{74{,}970} captions), with comprehensive linguistic analysis showing that 52.8% of the vocabulary is at risk of diacritic collision.

We present RADIO-ViPE (Reduce All Domains Into One -- Video Pose Engine), an online semantic SLAM system that enables geometry-aware open-vocabulary grounding, associating arbitrary natural language queries with localized 3D regions and objects in dynamic environments. Unlike existing approaches that require calibrated, posed RGB-D input, RADIO-ViPE operates directly on raw monocular RGB video streams, requiring no prior camera intrinsics, depth sensors, or pose initialization. The system tightly couples multi-modal embeddings -- spanning vision and language -- derived from agglomerative foundation models (e.g., RADIO) with geometric scene information. This coupling takes place in initialization, optimization and factor graph connections to improve the consistency of the map from multiple modalities. The optimization is wrapped within adaptive robust kernels, designed to handle both actively moving objects and agent-displaced scene elements (e.g., furniture rearranged during ego-centric session). Experiments demonstrate that RADIO-ViPE achieves state-of-the-art results on the dynamic TUM-RGBD benchmark while maintaining competitive performance against offline open-vocabulary methods that rely on calibrated data and static scene assumptions. RADIO-ViPE bridges a critical gap in real-world deployment, enabling robust open-vocabulary semantic grounding for autonomous robotics and unconstrained in-the-wild video streams. Project page: https://be2rlab.github.io/radio_vipe

Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or modality-agnostic, relying on idealized priors that ignore the layer-dependent modality fusion patterns in MoE-VLMs and provide little guidance for expert specialization. We propose Soft Modality-guided Expert Specialization (SMoES), which consists of dynamic soft modality scores that capture layer-dependent fusion patterns, an expert binning mechanism aligned with expert-parallel deployment, and an inter-bin mutual information regularization that encourages coherent modality specialization. Our method leverages attention-based or Gaussian-statistics modality scores to optimize mutual information regularization. Experiments across four MoE-based VLMs and 16 benchmarks demonstrate improvement on both effectiveness and efficiency: 0.9% and 4.2% average gain on multimodal and language-only tasks, 56.1% reduction in EP communication overhead, and 12.3% throughput improvement under realistic deployment. These results validate that aligning routing with modality-aware expert specialization unlocks MoE-VLM capacity and efficiency.

Multimodal affective computing analyzes user-generated social media content to predict emotional states. However, a critical gap remains in understanding how visual content shapes cognitive interpretations and elicits specific affective experiences such as pleasure. This study introduces a novel computational model to infer video-induced pleasure via cognitive appraisal variables. The proposed model addresses four challenges: (1) noisy and inconsistent human labels, (2) the semantic gap between "positive emotions" and "pleasure," (3) the scarcity of pleasure-specific datasets, and (4) the limited interpretability of existing black-box fusion methods. Our approach integrates data-driven and cognitive theory-driven methods, using cognitive appraisal theory and a fuzzy model within an innovative framework. The model employs transformer-based architectures and attention mechanisms for fine-grained multimodal feature extraction and interpretable fusion to capture both inter- and intra-modal dynamics associated with pleasure. This enables the prediction of underlying appraisal variables, thereby bridging the semantic gap and enhancing model explainability beyond conventional statistical associations. Experimental results validate the efficacy of the proposed method in detecting video-induced pleasure, achieving a peak accuracy of 0.6624 in predicting pleasure levels. These findings highlight promising implications for affective content recommendation, intelligent media creation, and advancing our understanding of how digital media influences human emotions.

Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or sensor configuration changes. We propose ViLiNT a multimodal, attention-based policy for goal navigation, trained on heterogeneous data from multiple platforms and environments, which improves robustness with two key features. First, we fuse RGB images, 3D LiDAR point clouds, a goal embedding and a robot's embodiment descriptor with a transformer architecture to capture complementary geometry and appearance cues. The transformer's output is used to condition a diffusion model that generates navigable trajectories. Second, using automatically generated offline labels, we train a path clearance prediction head for scoring and ranking trajectories produced by the diffusion model. The diffusion conditioning as well as the trajectory ranking head depend on a robot's embodiment token that allows our model to generate and select trajectories with respect to the robot's dimensions. Across three simulated environments, ViLiNT improves Success Rate on average by 166% over equivalent state-of-the-art vision-only baseline (NoMaD). This increase in performance is confirmed through real-world deployments of a rover navigating in obstacle fields. These results highlight that combining multimodal fusion with our collision prediction mechanism leads to improved off-road navigation robustness.

Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing methods achieve high accuracy on standard benchmarks but rely on heavy backbone architectures that preclude real-time deployment on embedded hardware. We present EfficientPENet, a two-branch depth completion network that replaces the conventional ResNet encoder with a modernized ConvNeXt backbone, introduces sparsity-invariant convolutions for the depth stream, and refines predictions through a Convolutional Spatial Propagation Network (CSPN). The RGB branch leverages ImageNet-pretrained ConvNeXt blocks with Layer Normalization, 7x7 depthwise convolutions, and stochastic depth regularization. Features from both branches are merged via late fusion and decoded through a multi-scale deep supervision strategy. We further introduce a position-aware test-time augmentation scheme that corrects coordinate tensors during horizontal flipping, yielding consistent error reduction at inference. On the KITTI depth completion benchmark, EfficientPENet achieves an RMSE of 631.94 mm with 36.24M parameters and a latency of 20.51 ms, operating at 48.76 FPS. This represents a 3.7 times reduction in parameters and a 23 times speedup relative to BP-Net, while maintaining competitive accuracy. These results establish EfficientPENet as a practical solution for real-time depth completion on resource-constrained edge platforms such as the NVIDIA Jetson.

Automating medical reports for retinal images requires a sophisticated blend of visual pattern recognition and deep clinical knowledge. Current Large Vision-Language Models (LVLMs) often struggle in specialized medical fields where data is scarce, leading to models that overfit and miss subtle but critical pathologies. To address this, we introduce DREAM (Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion), a novel framework for high-fidelity medical report generation that excels even with limited data. DREAM employs a unique two-stage fusion mechanism that intelligently integrates visual data with clinical keywords curated by ophthalmologists. First, the Abstractor module maps image and keyword features into a shared space, enhancing visual data with pathology-relevant insights. Next, the Adaptor performs adaptive multi-modal fusion, dynamically weighting the importance of each modality using learnable parameters to create a unified representation. To ensure the model's outputs are semantically grounded in clinical reality, a Contrastive Alignment module aligns these fused representations with ground-truth medical reports during training. By combining medical expertise with an efficient fusion strategy, DREAM sets a new state-of-the-art on the DeepEyeNet benchmark, achieving a BLEU-4 score of 0.241, and further demonstrates strong generalization to the ROCO dataset.

Breast cancer is a leading cause of cancer-related mortality worldwide, and timely accurate diagnosis is critical to improving survival outcomes. While convolutional neural networks (CNNs) have demonstrated strong performance on histopathology image classification, and machine learning models on structured electronic health records (EHR) have shown utility for clinical risk stratification, most existing work treats these modalities in isolation. This paper presents a systematic multimodal framework that integrates patch-level histopathology features from the BreCaHAD dataset with structured clinical data from MIMIC-IV. We train and evaluate unimodal image models (a simple CNN baseline and ResNet-18 with transfer learning), unimodal tabular models (XGBoost and a multilayer perceptron), and an intermediate-fusion model that concatenates latent representations from both modalities. ResNet-18 achieves near-perfect accuracy (1.000) and AUC (1.000) on three-class patch-level classification, while XGBoost achieves 98% accuracy on the EHR prediction task. The intermediate fusion model yields a macro-average AUC of 0.997, outperforming all unimodal baselines and delivering the largest improvements on the diagnostically critical but class-imbalanced mitosis category (AUC 0.994). Grad-CAM and SHAP interpretability analyses validate that model decisions align with established pathological and clinical criteria. Our results demonstrate that multimodal integration delivers meaningful improvements in both predictive performance and clinical transparency.

We introduce C-GenReg, a training-free framework for 3D point cloud registration that leverages the complementary strengths of world-scale generative priors and registration-oriented Vision Foundation Models (VFMs). Current learning-based 3D point cloud registration methods struggle to generalize across sensing modalities, sampling differences, and environments. Hence, C-GenReg augments the geometric point cloud registration branch by transferring the matching problem into an auxiliary image domain, where VFMs excel, using a World Foundation Model to synthesize multi-view-consistent RGB representations from the input geometry. This generative transfer, preserves spatial coherence across source and target views without any fine-tuning. From these generated views, a VFM pretrained for finding dense correspondences extracts matches. The resulting pixel correspondences are lifted back to 3D via the original depth maps. To further enhance robustness, we introduce a "Match-then-Fuse" probabilistic cold-fusion scheme that combines two independent correspondence posteriors, that of the generated-RGB branch with that of the raw geometric branch. This principled fusion preserves each modality inductive bias and provides calibrated confidence without any additional learning. C-GenReg is zero-shot and plug-and-play: all modules are pretrained and operate without fine-tuning. Extensive experiments on indoor (3DMatch, ScanNet) and outdoor (Waymo) benchmarks demonstrate strong zero-shot performance and superior cross-domain generalization. For the first time, we demonstrate a generative registration framework that operates successfully on real outdoor LiDAR data, where no imagery data is available.

Reliable UAV object detection requires robustness to illumination changes, motion blur, and scene dynamics that suppress RGB cues. Thermal long-wave infrared (LWIR) sensing preserves contrast in low light, and event cameras retain microsecond-level temporal edges, but integrating all three modalities in a unified detector has not been systematically studied. We present a tri-modal framework that processes RGB, thermal, and event data with a dual-stream hierarchical vision transformer. At selected encoder depths, a Modality-Aware Gated Exchange (MAGE) applies inter-sensor channel and spatial gating, and a Bidirectional Token Exchange (BiTE) module performs bidirectional token-level attention with depthwise-pointwise refinement, producing resolution-preserving fused maps for a standard feature pyramid and two-stage detector. We introduce a 10,489-frame UAV dataset with synchronized and pre-aligned RGB-thermal-event streams and 24,223 annotated vehicles across day and night flights. Through 61 controlled ablations, we evaluate fusion placement, mechanism (baseline MAGE+BiTE, CSSA, GAFF), modality subsets, and backbone capacity. Tri-modal fusion improves over all dual-modal baselines, with fusion depth having a significant effect and a lightweight CSSA variant recovering most of the benefit at minimal cost. This work provides the first systematic benchmark and modular backbone for tri-modal UAV-based object detection.

Omni-modal Large Language Models (Omni-MLLMs) promise a unified integration of diverse sensory streams. However, recent evaluations reveal a critical performance paradox: unimodal baselines frequently outperform joint multimodal inference. We trace this perceptual fragility to the static fusion topologies universally employed by current models, identifying two structural pathologies: positional bias in sequential inputs and alignment traps in interleaved formats, which systematically distort attention regardless of task semantics. To resolve this functional rigidity, we propose Chain of Modality (CoM), an agentic framework that transitions multimodal fusion from passive concatenation to dynamic orchestration. CoM adaptively orchestrates input topologies, switching among parallel, sequential, and interleaved pathways to neutralize structural biases. Furthermore, CoM bifurcates cognitive execution into two task-aligned pathways: a streamlined Direct-Decide'' path for direct perception and a structured Reason-Decide'' path for analytical auditing. Operating in either a training-free or a data-efficient SFT setting, CoM achieves robust and consistent generalization across diverse benchmarks.

Recent advances in multimodal audio generation have enabled music synthesis from text, visual cues, and other high-level conditions. However, most systems are designed for a single operating mode: either generating music without a reference mixture or extracting a target source from an existing mixture. This fixed-task design limits their use when different combinations of text, visual, and mixture inputs are available. To address this gap, we propose MAGE, a modality-agnostic framework for conditional music generation and mixture-grounded target-source extraction within a shared continuous latent space. Our approach introduces three key components. First, a Controlled Multimodal FluxFormer models the conditional flow from noise to a target audio latent, enabling the same backbone to operate with or without a mixture condition. Second, Audio-Visual Nexus Alignment maps frame-level visual features onto the audio latent sequence, allowing visual evidence to condition the generation process at the audio-token level. Third, a cross-gated modulation mechanism uses the aligned visual representation to regulate intermediate audio features, while text provides separate semantic guidance. We further train MAGE with dynamic modality masking, exposing the same model to text-only, visual-only, joint text-visual, mixture-conditioned, and unconditional configurations. Experiments on the MUSIC benchmark evaluate MAGE under separate protocols for mixture-free generation and mixture-grounded target-source extraction. The results show that MAGE provides a shared conditioning interface across both settings, and that the proposed alignment and gating components improve interference suppression in the extraction task.

Multimodal semantic segmentation has shown great potential in leveraging complementary information across diverse sensing modalities. However, existing approaches often rely on carefully designed fusion strategies that either use modality-specific adaptations or rely on loosely coupled interactions, thereby limiting flexibility and resulting in less effective cross-modal coordination. Moreover, these methods often struggle to balance efficient information exchange with preserving the unique characteristics of each modality across different modality combinations. To address these challenges, we propose CrossWeaver, a simple yet effective multimodal fusion framework for arbitrary-modality semantic segmentation. Its core is a Modality Interaction Block (MIB), which enables selective and reliability-aware cross-modal interaction within the encoder, while a lightweight Seam-Aligned Fusion (SAF) module further aggregates the enhanced features. Extensive experiments on multiple multimodal semantic segmentation benchmarks demonstrate that our framework achieves state-of-the-art performance with minimal additional parameters and strong generalization to unseen modality combinations.

Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions about source reliability, limiting their ability to resolve conflicts when a modality becomes unreliable due to situational factors such as sensor degradation or class-specific corruption. We introduce C$^2$MF, a context-specfic credibility-aware multimodal fusion framework that models per-instance source reliability using a Conditional Probabilistic Circuit (CPC). We formalize instance-level reliability through Context-Specific Information Credibility (CSIC), a KL-divergence-based measure computed exactly from the CPC. CSIC generalizes conventional static credibility estimates as a special case, enabling principled and adaptive reliability assessment. To evaluate robustness under cross-modal conflicts, we propose the Conflict benchmark, in which class-specific corruptions deliberately induce discrepancies between different modalities. Experimental results show that C$^2$MF improves predictive accuracy by up to 29% over static-reliability baselines in high-noise settings, while preserving the interpretability advantages of probabilistic circuit-based fusion.