Overview

Cross-modal attention studies how information from one modality—such as text, images, audio, video, or sensor data—can guide the representation of another. It matters for tasks including visual question answering, retrieval, medical diagnosis, speech separation, and autonomous systems, where useful evidence may be distributed across inputs. Common approaches include bidirectional or asymmetric cross-attention, query- and register-based fusion, and sparse, local, or temporally guided attention, sometimes combined with confidence gating or feature disentanglement. Performance has improved across many benchmarks, but reliable fusion remains difficult when modalities are misaligned, unevenly informative, or prone to dominating one another; attention patterns also do not always guarantee faithful grounding or reasoning.

Latest papers

93 papers6 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Nov 7, 2026

Guided Co-Attention with Adaptive Gating for Multimodal Medical Data Fusion

Multimodal fusion requires not only exchanging information across modalities but also determining which representations should participate in the interaction and how complementary cross-modal views should be combined. We introduce Guided Co-Attention with Adaptive Gating, a fusion framework that integrates token-wise guidance, bidirectional cross-attention, and sample-specific fusion. The proposed method constructs two directional representations: an image-conditioned text representation, obtained by allowing textual tokens to query visual features, and a text-conditioned image representation formed in the reverse direction. Token-wise guidance modulates the representations before cross-attention, while an adaptive gate learns the relative contribution of the two resulting directional representations for each sample. We evaluate the approach using paired chest radiographs and radiology reports as an image-text test bed for binary (normal vs. abnormal) classification. The two cross-attention directions exhibit distinct performance characteristics, demonstrating that reversing the query and source modalities does not produce interchangeable representations. Ablation experiments further show that bidirectional interaction, adaptive gating, and token guidance provide complementary benefits. The proposed model achieves 96.05% accuracy, 96.10% F1-score, 98.37% AUC, 95.60% Sens@95Spec, and 96.51% Spec@95Sens, yielding the highest mean performance across all evaluated metrics. These findings support explicitly modeling interaction direction, token relevance, and sample-dependent integration when constructing multimodal representations.
Oct 27, 2026

Grounding Long Financial Text with Semantically-Enriched Tables via Multimodal Learning

We propose a multimodal transformer framework for efficiently modeling long1 financial documents that combine structured tabular data with noisy, unstructured2 textual disclosures. The framework represents financial tables as semantically3 enriched token sequences and integrates them with long-form text through a cross-4 attention mechanism that explicitly captures cross-modal dependencies. In par-5 ticular, we augment each numerical variable with a semantic embedding derived6 from its textual definition, enabling the model to encode both numerical magnitude7 and economic meaning. This design yields a more expressive and parameter-8 efficient representation of tabular data compared to value-only embeddings. Using9 a large-scale dataset of financial statements and MD&A disclosures, we show that10 structured numerical features remain the dominant source of predictive signal;11 however, textual information provides consistent incremental gains when incor-12 porated via cross-attention rather than simple concatenation. Our results further13 demonstrate that noisy textual disclosures are most useful when conditioned on a14 stable, semantically structured tabular representation. In particular, using frozen15 variable-level tabular representations as cross-attention queries enables the model16 to weight MD&A chunks differently for each financial variable and observation.17 These findings suggest that cross-attention provides an efficient mechanism for18 table-conditioned aggregation of long-form narrative evidence.
Oct 20, 2026

Revealing Inter-Channel Modality Discriminability: Channel Selective Interaction Fusion Network for Optical-SAR Object Detection

Synthetic aperture radar (SAR) and optical imagery provide complementary structural and appearance information for remote sensing object detection. However, substantial cross-modal discrepancies and indiscriminate channel interaction inevitably introduce redundant or conflicting features. Since different feature channels encode heterogeneous semantic information and contribute unequally to cross-modal fusion, selectively highlighting task-relevant channels while suppressing redundant ones is essential. To address this issue, we propose the Channel Selective Interaction Fusion Network (CSIF-Net), which performs selective channel-level cross-modal interaction. CSIF-Net first employs a frequency decomposition module to construct frequency-aware SAR inputs, facilitating the separation of structural information from noise-related responses. It then models cross-modal channel relationships through a cross-attention channel selection module and dynamically partitions the features into shared and modality-specific components. Finally, a dual-branch fusion module performs cross-modal interaction and channel realignment for shared features while independently enhancing SAR-specific features, thereby exploiting complementary information and suppressing modality interference. Extensive experiments on the OGSOD 1.0 and M4-SAR datasets demonstrate that CSIF-Net achieves state-of-the-art performance in both horizontal and oriented object detection, surpassing the existing methods by 4.01% and 3.18% gains, respectively.
Oct 19, 2026

SleepPairNet: Learning Multimodal Pediatric Sleep Representations with Random-Pair Cross-Attention

Analyzing physiological sleep signals is important for assessing sleep quality and detecting sleep-related disorders. Learning inter-modal relationships across physiological signals can provide richer representations for downstream sleep analysis. We introduce SleepPairNet, a multimodal self-supervised learning (SSL) framework that learns pairwise interactions between physiological signals through cross-attention. We propose a random modality-pair selection strategy that exposes the model to diverse signal pairs during pretraining, enabling flexibility across modality combinations at test time. Pretrained on the NCH dataset, SleepPairNet outperforms the evaluated SSL baselines on all respiratory tasks while remaining competitive on EEG-related tasks, and shows even stronger results when transferred to the external CHAT dataset.
Oct 16, 2026

STC-MGNet: Spatial-Temporal-Channel Attention-Enhanced Multimodal Graph Network for Pedestrian Intention Prediction

Accurate prediction of pedestrian crossing intentions plays a critical role in enhancing the safety of pedestrian-vehicle interactions in autonomous driving. However, effectively capturing subtle spatiotemporal patterns in pedestrian pose sequences and integrating complementary visual and ego-vehicle motion information remain challenging. This paper proposes a spatial-temporal-channel attention-enhanced multimodal graph network (STC-MGNet) for pedestrian crossing intention prediction. STC-MGNet introduces a spatial-temporal-channel (STC) attention-enhanced pose graph encoder to learn discriminative representations from pedestrian pose sequences. Three parallel attention branches selectively emphasize informative skeletal joints, observation frames, and feature channels, with their outputs integrated through learnable fusion weights. To leverage complementary visual and ego-vehicle motion information, a multi-stage cross-modal channel modulation mechanism is introduced to adaptively refine pose representations through modality-specific channel gating at successive graph encoding stages. Experimental results demonstrate that STC-MGNet achieves accuracy rates of 70%, 87%, and 88% on the JAADbeh, JAADall, and PIE datasets, respectively, outperforming several representative baseline methods. Ablation experiments further highlight the complementary contributions of visual and ego-vehicle motion information to prediction performance.
Oct 13, 2026

Focus on What You Need: Global-to-Local Dynamic Attention for Multimodal Sarcasm Detection

Multimodal sarcasm detection has attracted increasing attention due to the widespread use of images and text on social media platforms. Existing studies generally treat the semantic or emotional inconsistency between images and text as a key cue for identifying sarcastic expressions. However, images in real-world scenarios often contain multiple visual objects, many of which are irrelevant to sarcasm-related semantics. Such redundant visual information may introduce noise during cross-modal interaction, distracting models from focusing on critical sarcasm cues and potentially leading to inaccurate predictions. To address this issue, we propose GLDA (Global-to-Local Dynamic Attention), a multimodal sarcasm detection framework that models cross-modal interactions from a global-to-local perspective. Specifically, GLDA first employs a global multimodal fusion module to capture high-level semantic interactions between visual and textual modalities, enabling the model to identify coarse-grained cross-modal inconsistencies. To further reduce the influence of irrelevant objects, GLDA introduces a local gated cross-modal attention mechanism that dynamically filters redundant visual and textual features and refines multimodal representations at a finer granularity. In addition, a multi-branch learning objective is designed to jointly optimize unimodal and multimodal representations. Experimental results demonstrate that GLDA effectively improves sarcasm detection performance and achieves competitive results compared with existing approaches. The code will be available at https://anonymous.4open.science/r/GLDA-DBE6.
Oct 5, 2026

Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings

Breast cancer is the leading cause of cancer-related mortality among women in Sub-Saharan Africa, where delayed diagnosis results from limited radiology expertise and fragmented clinical data systems. Although deep learning models have demonstrated strong performance in mammographic analysis, most rely solely on imaging data and are trained on Western populations, limiting their applicability in African healthcare settings. This paper presents a Hybrid Cross-Modal Attention Network (HCMAN) that integrates mammogram images with structured clinical data using transformer-based cross-modal attention mechanisms. The model was developed and validated using a locally collected dataset of 2,560 mammogram images from 1,024 patients across four Ethiopian referral hospitals, with biopsy-confirmed ground truth labels. The proposed framework achieves 97.8% accuracy, 97.2% sensitivity, 98.3% specificity, and an AUC of 0.987, significantly outperforming image-only baselines. The system demonstrates robustness to low-quality images typical of resource-limited settings, with only 3.2% performance degradation compared to 8.7% for image-only models. Cross-modal attention analysis reveals clinically appropriate behavior: higher reliance on clinical features for ambiguous cases such as dense breasts and young patients. The model's lightweight architecture enables deployment on standard hospital workstations (<2 seconds inference on CPU). This work advances sustainable, context-aware AI solutions for equitable breast cancer diagnostics in Africa.
Oct 2, 2026

Architecture-Dependent Fusion Pathways in MLLMs

Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textual information are fused across layers remain insufficiently understood. We investigate representative MLLMs from two architectural paradigms: concatenation architectures and native multimodal architectures. We conduct three progressively connected analyses: alignment decoupling identifies which modality changes, attention routing and entropy characterize how cross-modal information is distributed, and intrinsic dimensionality examines how fusion reshapes feature spaces. Separately, we perform causal intervention experiments as a validation of the resulting interpretation. As a supplementary analysis, we use visual CKA to examine the Platonic Representation Hypothesis. Together, these analyses reveal two distinct fusion pathways: concatenation models follow a text-first, vision-later pathway, whereas native models exhibit earlier visual-textual co-adaptation and feature-space reorganization. This work provides a mechanistic perspective for understanding multimodal fusion and supports architecture-aware diagnostics of multimodal representations.
Oct 2, 2026

Register-Routed Delayed Fusion: Rewiring Shortcut-Prone Observation Fusion in Visuomotor Imitation

Visuomotor imitation policies combine high-dimensional visual observations with compact signals such as proprioception, and their fusion topology determines when and through which tokens these streams interact. In dense token fusion, visual tokens may attend directly to compact tokens from the first encoder layer, allowing action-predictive compact cues to influence spatial visual representations early in their formation. We ask whether controlling this route improves visual responsiveness and policy behavior. We introduce Register-Routed Delayed Fusion (RRDF), which masks direct compact-visual attention and stages cross-modal interaction through a learned register workspace. Its isolate-collect-route schedule protects an early stream-separated prefix and later permits only register-mediated exchange, while compact conditioning remains available to the native action generator. Across five simulation tasks and three real-robot tasks, RRDF matches or improves dense ACT under nominal conditions. Appearance-shift evaluations on four simulation tasks and held-out-position evaluations on three real-robot tasks also favor RRDF. Phase-matched input probes show lower measured state-to-image sensitivity, while ablations indicate that adding registers alone does not reproduce the full performance gain. These results support controlling cross-modal propagation while retaining compact action conditioning.
Oct 2, 2026

GAANet: Global-guided Asymmetric Attention Network for Audio-Visual Speech Separation

Multi-scale design is crucial for efficient audio-visual speech separation, yet effectively modeling multi-scale information for audio-visual feature fusion remains challenging. We argue that the limited capacity of existing approaches primarily arises from: 1) treating features from different modalities in the same manner, and 2) overlooking the role of global features. To address these issues, we propose a Global-guided Asymmetric Attention Network (GAANet). Our model introduces two core innovations: first, an asymmetric multi-scale fusion framework that allows audio and visual streams to extract and interact with features at their respective optimal temporal resolutions, removing the need for symmetric temporal downsampling; second, a global-guided attention mechanism that compresses each modality into a compact global token with a temporal dimension of one, which then provides high-level semantic cues to guide both intra- and inter-modal fusion across scales. Experiments on LRS2 and VoxCeleb2 demonstrate that GAANet achieves state-of-the-art performance, reaching 16.5 dB SI-SNRi on LRS2 and 14.0 dB on VoxCeleb2, while maintaining a lightweight computational profile with only 3.3M parameters and 19.8G MACs. These results highlight the strong potential of asymmetric temporal modeling and global guidance for efficient and robust multimodal fusion. The source code is publicly accessible at https://github.com/redizzy/GAANet
Oct 1, 2026

Fusing Visual and Textual Representations via Multi-layer Fusing Transformers for Vietnamese Visual Question Answering

In recent decades, artificial intelligence has made significant progress in understanding and interacting with images. One of the important applications of this technology is Visual Question Answering (VQA), a research field that requires computers to understand and answer questions about images in a natural manner. Despite extensive research and development in VQA for English, there have been very few similar efforts made for other languages, especially Vietnamese. This gap presents a significant challenge and opportunity for the advancement of VQA technology in the Vietnamese language context. By bridging this gap, the field of Vietnamese VQA not only enriches the diversity of research in artificial intelligence but also enables practical applications in various domains, such as education, healthcare, and entertainment, catering to Vietnamese-speaking populations worldwide. Thus, the exploration and development of Vietnamese VQA systems hold immense potential for advancing both research and practical applications in the intersection of computer vision and natural language processing. In this paper, we propose a Multi-layer Fusing Transformer model utilizing a cross attention module to combine multiple modality features of images and texts from different layers in an aggregated representation. Our architecture allows us extract information from low level to high level. Through detailed experiments and ablation studies, our model achieves promising results against the competitive baselines in ViVQA dataset for Vietnamese language.
Sep 24, 2026

Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration

Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, often generating answers without adequately using task-relevant visual evidence. Existing approaches primarily improve reasoning through reasoning-oriented supervision or inference-time strategies. In this work, we study a complementary question: can multimodal reasoning be improved by strengthening implicit visual grounding without directly supervising the reasoning process? Motivated by the functional specialization of attention heads, we investigate whether reasoning can be improved by guiding only the heads most responsive to visual evidence grounding. We propose Selective Probability Mass Concentration (sPMC), a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention. sPMC treats normalized attention over visual tokens as a spatial probability distribution and encourages the probability mass to be assigned to semantically relevant regions using segmentation-derived spatial priors. Adaptive Head Selection restricts this guidance to visually responsive heads while leaving the remaining heads unconstrained to preserve their complementary functions. Across 6 multimodal benchmark suites, sPMC achieves an average zero-shot improvement of 3% and gains of up to 11.3% across multiple MLLMs while regularizing only 3%-15% of their attention heads. These results demonstrate that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.
Sep 23, 2026

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrower aspects of the same event. We find that joint multimodal diffusion transformers exhibit a corresponding asymmetry in cross-modal correspondence: companion modalities develop strong correspondences to video, but the reciprocal correspondences through which they constrain video remain substantially weaker. We express both directions as comparable correspondence distributions over video tokens and define their disagreement as the reciprocal correspondence gap. We introduce RecCAR, standing for Reciprocal Cross-modal Attention Regularization, a KL regularizer that uses the well-established video-to-modality correspondence as a fixed reference and aligns the weaker modality-to-video correspondence toward it. Across joint video-motion and video-audio generation, RecCAR improves the Human Anatomy score from 0.69 to 0.75 and reduces audio-video desynchronization from 0.804 to 0.752, while improving overall generation
Sep 23, 2026

S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detection

Alignment-free RGB-T salient object detection (RGB-T SOD) aims to identify salient objects from unregistered RGB and thermal image pairs without costly pre-alignment. However, spatial misalignment breaks pixel-wise correspondence and causes feature contamination during cross-modal fusion. To address this issue, we propose S2A, a semantic-to-spatial alignment framework for alignment-free RGB-T SOD. Specifically, a global-guided hierarchical fusion module (GGHF) first exploits global semantic guidance to suppress background interference and refine hierarchical intra-modal features. Subsequently, the alignment-free cross-modal channel attention module (AFCA) globally exchanges complementary semantic information through channel-wise interaction, effectively overcoming the interference caused by local spatial misalignments. Finally, a spatial deformable cross-attention module (SDCA) predicts adaptive sampling offsets to recover local cross-modal spatial correspondence. Through this semantic-to-spatial paradigm, S2A first enables reliable cross-modal semantic interaction and subsequently performs local spatial calibration, effectively reducing misalignment-induced feature contamination. Without bells and whistles, S2A achieves highly competitive performance on multiple public alignment-free RGB-T benchmarks, demonstrating its effectiveness in alleviating misalignment-induced feature contamination.
Sep 17, 2026

Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models

Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantially more robust---e.g., rephrasing "Is there a cat?" into "Please look carefully and answer: is there a cat?". Conversely, VLMs become more fragile under corruption when the question is semantically complex or finer-grained, e.g., "what colour is the cup left of the chair?" instead of "is there a cup?". Both effects stem from question-conditioned cross-modal attention, which induces a spectral filter over image patches: verbose questions broaden its frequency support, while fine-grained questions concentrate it onto fewer visual scales. The model's answer drifts most when this filter and the corruption sit on the same spatial frequencies. We test the filter view on Qwen3-VL and LLaVA-OneVision across GQA and CLEVR; verbose paraphrasing reduces drift variance by 70--81% on the 8B models. The practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.
Sep 3, 2026

The Attention Triangle in Audio-Video Models

Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the ``attention triangle,'' comprising the three cross-attention edges connecting the text, audio, and video streams, and examine how semantic information is routed across modalities during generation. Our analysis reveals that routing along the audio-video edge is bidirectional: audio can influence video generation, while video can influence audio generation. This edge is shaped by biases encoded in the model's parameters and emerges as a major contributor to leakage: when prompts are in tension with learned priors, cross-modal interactions may override the intended conditioning and reroute semantics toward visually canonical but incorrect outcomes. These effects suggest that semantic artifacts arise not merely from attention spreading beyond its intended target, but from structured, bias-driven interactions along specific pathways. Building on this perspective, we extract attention-derived signals that expose how semantics are distributed and grounded across modalities, and use them as a diagnostic tool to both analyze and deliberately incur leakage under controlled conditions. This enables us to probe the internal dynamics of cross-modal routing and isolate the role of individual interactions. We further leverage these signals to guide inference-time interventions that encourage more consistent cross-modal alignment. Extensive experiments support our analysis and demonstrate improved semantic grounding while preserving generation quality.
Sep 1, 2026

IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion

Text-guided image fusion has recently emerged as an effective paradigm for integrating multi-modal information while enabling flexible and task-oriented fusion control. However, existing text-guided fusion methods often rely on shallow semantic-visual interaction and limited attention mechanisms, which restrict their ability to robustly handle complex degradations and fully exploit textual guidance. In this paper, we propose an iterative text-guided image fusion framework that incorporates text-conditioned feature interaction across multiple fusion and refinement stages. The proposed method integrates deepest-level Cross-Attention, multi-scale Cross-Gate Fusion, and stage-specific text-conditioned modulation, allowing the global text embedding to condition hierarchical feature fusion and residual refinement. By repeatedly injecting the pooled text embedding across hierarchical decoder and refinement stages, the proposed framework provides degradation-aware global semantic conditioning while preserving complementary information from the visible and infrared modalities. Experiments on several benchmark datasets show that the proposed method improves several information-preservation and perceptual-quality metrics, while exhibiting metric-dependent trade-offs on some datasets.
Aug 24, 2026

Modalities Should Talk to Each Other: Dual-Stream Multimodal Learning for Long-Horizon Influenza Forecasting

Forecasting long-range influenza-like illness (ILI) matters for public health readiness. Publicly available surveillance datasets typically pair numeric epidemiological signals with textual information that is noisy, loosely structured, only indirectly related to near-term trends, and often lagged relative to the numeric signal. Fusing the two therefore requires careful design. We propose Dual-Stream Attention (DSA), a multimodal deep learning framework that forecasts 12-week-ahead ILI activity from a 36-week multimodal history by letting the numerical and textual streams condition each other. Using the Time-MMD health-domain dataset, DSA separately encodes the two modalities with a Transformer-based numerical encoder and a domain-adapted headline encoder, then couples them through a bidirectional Cross-Modal Attention (CMA) mechanism: the text (news headlines) conditions the interpretation of the numeric signal and vice versa. The CMA output then passes to a causal temporal model for forecasting. Evaluated across ten random seeds, DSA achieves a median test MSE of 0.416, versus 0.668, 0.607, and 0.851 for iTransformer, TaTS, and GPT4MTS, corresponding to mean-error reductions of 54.95%, 37.29%, and 67.23%, with paired Cohen's d of 0.555, 0.337, and 0.345, respectively, and ranks first in 100% of bootstrap draws. It also has substantially lower worst-window error than all baselines. On an external-geography dataset, DSA again ranks first among nine evaluated baselines. Ablations show the advantage does not depend on text-encoder choice or language-model fine-tuning, and that bidirectional attention outperforms either direction alone. Finally, perturbation-based faithfulness analysis shows the learned CMA is functionally informative under targeted masking, with a stronger effect in the text-to-numerical direction.
Aug 19, 2026

Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors

Estimating interpretable conditional-dependence structures from multimodal visual-linguistic features remains largely unexplored. We propose CM-GLasso (Cross-Modal Graphical Lasso), a framework that bridges vision-language representation learning and sparse Gaussian Graphical Models. CM-GLasso introduces three key components: (i) a text visualization strategy that renders class-attribute descriptions as images and processes them through the same SigLIP-2 vision encoder as natural images, yielding prototype-indexed patch-level attention footprints in a shared feature coordinate system; (ii) a cross-attention distillation mechanism that condenses high-dimensional patches into a small set of semantic graph nodes, whose attention-footprint similarities yield cross-modal structural priors for non-uniform L1 penalization; (iii) a joint ADMM formulation that estimates shared and class-specific precision components within a single convex objective, avoiding the need to first estimate and then decompose separate class-wise graphs. The learned sparse graph topologies directly support a parameter-free, precision-based classification rule and a lightweight topology-aware segmentation head. Extensive experiments on eight benchmarks demonstrate that CM-GLasso achieves competitive or superior performance compared with strong feature-based and task-specific baselines. Under the matched controlled protocol, it attains the highest average classification accuracy (91.97%) and the highest segmentation mIoU among the controlled baselines on VOC (74.75%) and ADE20K (64.01%), while also yielding explicit sparse conditional-dependence graphs with common-specific decomposition.
Aug 17, 2026

Multi-scale Decomposed Convolution Refinement Network for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) suffers from cross-modal discrepancies and limited discriminative capabilities, leading to suboptimal recognition performance. Current approaches exhibit limitations in semantic mining, cross-modal fusion and feature constraints. To tackle these challenges, we propose MDCRNet, a Multi-scale Decomposed Convolution Refinement Network that enhances cross-modal feature learning and discriminative metric learning. Specifically, we introduce a Hierarchical Learning Module (HLM) containing four Hierarchical Decomposed Convolution Attention (HDCA) modules, each equipped with lightweight channel attention and multi-scale spatial perception blocks to capture multi-scale spatial dependencies. Moreover, we develop a Joint Discriminative Metric Loss (JDML) incorporating a novel Granularity Discriminative Loss (GDL) that simultaneously optimizes intra-identity compactness and inter-identity separability across modalities. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that MDCRNet achieves state-of-the-art performance on both benchmarks. Code is available at https://github.com/Kevin-zms/MDCRNet.
Aug 16, 2026

Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse Attention

Recent audio-visual generation models can synthesize synchronized video and sound in a unified diffusion process, but their inference cost remains high because long video token sequences require repeated attention computation across denoising steps. A variety of acceleration techniques have been developed for video generation models, including low-bit quantization, attention sparsification, and feature caching. However, since these methods are originally designed for video generation, directly applying them to audio-visual models overlooks the interactions between the audio and video branches and may therefore disrupt audio-video synchronization. We present a synchronization-aware acceleration framework for efficient audio-visual generation. Our key observation is that bidirectional audio-video cross-attention reveals structured interactions between the two branches, with high responses often concentrated on a few sound-related visual and temporal regions. Guided by this interaction pattern, we introduce a protected sparse attention strategy that preserves high-fidelity computation for synchronization-critical tokens while sparsifying redundant attention interactions. By explicitly accounting for cross-modal dependence during acceleration, our method improves inference efficiency while keeping video quality, audio quality, and audio-video synchronization.
Aug 6, 2026

CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection

Multispectral object detection combines visible and thermal imagery to improve perception under challenging illumination and environmental conditions. However, differences in modality appearance and reliability can introduce redundant or conflicting responses, limiting the use of complementary information. Complex fusion mechanisms further increase computational cost, creating a persistent trade-off between detection accuracy and efficiency. To address these challenges, CFGPNet is proposed, a cross-attention-based fused gradient programmed network. The framework incorporates re-parameterized RepViT blocks into the YOLOv9 architecture to strengthen spatial and channel representations while maintaining efficient feature extraction. Cross Computation Efficient Attention (CrossCEA) exchanges spatial attention maps between modalities at multiple detection scales, allowing each stream to emphasize regions supported by the other while preserving modality-specific information. Attention Selection and Aggregation Fusion (ASAF) combines dense feature aggregation with selection of the strongest responses from multiple attention branches to form compact, discriminative fused representations. A programmable gradient information pathway provides auxiliary supervision during training to improve feature learning. This pathway is removed after training, adding no parameters or operations at inference. Experiments on FLIR, M3FD, LLVIP, VEDAI, and MFAD demonstrate favorable accuracy-efficiency trade-offs across three model scales, with the smallest variant requiring 15.3 million parameters and 56.9 GFLOPs. The code is available at https://github.com/NimaHatami99/CFGPNet.
Aug 5, 2026

C3^3PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models

Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modality, resulting in brittle cross-modal reasoning. We introduce C3^3PO, a benchmark of 3,404 samples spanning video, audio, image, and text, evaluating two abilities: information composition (fusing dispersed evidence) and counterfactual conflict (resolving deliberate contradictions). C3^3PO's paired IC/CC structure and four-tier design enable targeted diagnosis of when and why cross-modal reasoning fails. Built through a fully automatic pipeline using 25 logically grounded templates, C3^3PO reveals that while humans achieve 88.64% accuracy, the best model (Gemini-3.1-Pro) reaches only 73.17%, with open-source models collapsing under conflict. Through attention probes, we find 86-95% of failures stem from modality dominance: models commit to one modality while ignoring contradictory evidence, concentrating 87-95% of attention on text. Mid-layer attention entropy predicts correctness-sustained exploration succeeds, premature collapse fails. The 56-point accuracy gap between equally complex templates reveals that performance depends on modalities' structural roles in conflict resolution, not combinations. These findings show multimodal perception does not guarantee robust reasoning; architectures must enable sustained cross-modal attention to avoid premature
Aug 5, 2026

RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection

RGB-infrared (RGB-IR) object detection benefits from complementary visible and thermal cues, but effective fusion remains challenging under illumination changes, weather variation, and cluttered scenes. Existing RGB-IR fusion methods often trade expressive patch-level interaction for lighter but more constrained adaptation mechanisms. We empirically observe that pretrained register tokens contain both modality-shared and modality-specific information on paired RGB-IR inputs, suggesting that they can serve as a compact substrate for cross-modal communication. Building on this observation, we propose RegisterBridgeMM, a register-mediated fusion framework organized as a three-stage register lifecycle. Aggregate preserves per-modality register summarization inherited from pretraining; Bridge performs bidirectional register-to-patch reading with consensus-residual regulation; and Project translates the resulting register summary into spatially adaptive calibration of patch features. This register pathway avoids dense patch-to-patch cross-modal interaction while preserving the pretrained patch representation. With both backbone streams frozen, RegisterBridgeMM achieves the highest mAP50-95 among the evaluated methods on all four benchmarks: LLVIP, M3FD, DroneVehicle, and FLIR-Aligned.
Aug 3, 2026

Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition

Deep multimodal fusion for object detection has demonstrated good performance through mining modal characteristics. However, existing feature-level fusion methods mainly weigh between two modalities and unify them in a unified representation space. This can lead to overfitting or over-specialization of the statistical properties of a single modality within a dual-backbone architecture. This paper proposes an Attention-Driven Complementarity Resampling framework for robust improvement of cross-modality object detection. Based on a shared channel spatial attention mechanism, we first introduce the semantic mask exchange to actively mix the boundaries of the modalities during the training phase, forcing the backbone network to learn generalized features without relying on fixed modal labels. Then we propose a learnable channel competition to sample and aggregate features in a channel-wise and learnable way. Our experiments on multiple datasets demonstrate that the proposed method is effective and yields competitive results among existing state-of-the-art approaches. The source code is provided in the supplementary material.
Aug 1, 2026

Generic Vision and Cross-Attention for Reaction Yield Prediction

Traditional reaction yield prediction is constrained by 1D quantum descriptors that lack explicit spatial information. To address this gap, a dual-modal Vision Cross-Attention architecture is proposed, fusing tabular physical-organic data with 2D molecular topologies. Notably, it is demonstrated that a generic computer vision backbone processing simple 2D skeletal structures independently outperforms purely quantum-based baselines. By synergizing both modalities, superior predictive accuracy compared to traditional methodologies is achieved by the optimal cross-attention framework (Test RMSE = 5.27%). Through mechanistic probing, active, descriptor-guided spatial querying is observed, effectively offloading macroscopic steric identification to the visual pathway. Furthermore, a dynamic chemical hierarchy is learned by the network to heavily prioritize critical steric bottlenecks, such as the aryl halide. Concurrently, residual skip connections are utilized to protect non-spatial electronic parameters from destructive attenuation during fusion. Collectively, a scalable and highly interpretable blueprint is provided for augmenting physical chemistry with deep visual learning.
Jul 27, 2026

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disproportionate attention toward certain semantically uninformative visual tokens, a phenomenon termed "register" or "Visual Attention Sinks." While existing inference intervention methods attempt to identify these sink tokens and redistribute their attention weights, such approaches typically treat these tokens in isolation and suffer from computational inefficiency. Instead, we reframe this phenomenon as a generalized textual bias exerted over visual features that extends beyond isolated sink tokens. From this perspective, a pervasive structural bias leads to the dilution of the semantic visual signal, precipitating multimodal hallucinations as the model prioritizes linguistic priors over valid visual evidence. To address this limitation, we introduce Saliency-guided Purification and Adaptive Redistribution (SPAR), a training-free, plug-and-play intervention. SPAR mitigates this generalized textual bias by purifying structural noise and subsequently redistributing the reclaimed attention budget to the most informative visual regions. Comprehensive evaluations across a diverse spectrum of hallucination benchmarks demonstrate that SPAR effectively restores authentic visual grounding with negligible computational overhead.
Jul 21, 2026

Advancing Multimodal Fusion on Heterogeneous Medical Data with Hybrid Geometry Attention

Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, clinical records, and omics. However, existing MFL strategies face several major challenges. First, they struggle to capture complex cross-modal interactions effectively, which in turn limits performance improvements. Second, they incur high computational costs, restricting their applicability in resource-constrained healthcare AI applications. Finally, they are often designed and evaluated for narrow, fixed modality configurations (e.g., imaging-only, or specific pairs such as image and omics), which limits evidence of their adaptability and generalizability to broader collections of heterogeneous medical modalities. To address these challenges, we propose a novel MFL framework - Cascaded Unified Representation Learning for Efficient Fusion Network (CURE) - a lightweight and scalable framework that progressively integrates various modalities through a novel efficient Hybrid Geometry Aware Fusion layer (HyFuse), where each HyFuse layer is sequentially learned for each modality, making the framework adaptable and generalizable. Within HyFuse, an efficient residual convolution module captures rich multi-scale features to ensure cost-effective learning, while a hybrid-space aware attention mixer learns coarse-to-fine structural cues to better preserve cross-modal relationships. Complementary learnable late-fusion and shared information refinement modules are then employed to learn robust modality-order-invariant shared representations, which in turn yields consistent performance improvements. Extensive evaluations on 16 public datasets show that CURE outperforms leading multimodal fusion methods, boosting performance by up to 3.97% and lowering computational costs by up to 87.8%, ensuring more effective and reliable predictions.
Jul 20, 2026

Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution

Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political video-text pairs automatically annotated via Qwen2.5-VL. By combining this analysis with self-supervised video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in multimodal systems.
Jul 14, 2026

Adaptive Cross-Modal Fusion with Sparse Attention for Pedestrian Crossing Intention Prediction

Predicting pedestrian crossing intention is a safety-critical task for autonomous driving, yet existing approaches often rely on single-modal inputs or dense multimodal fusion strategies that inadequately capture complementary visual and kinematic information while introducing redundant inter-modal interactions. We propose ADAPT (Adaptive Domain-Aware Pedestrian Crossing Transformer), a multimodal framework that jointly models local and global visual context together with temporal motion dynamics for accurate pedestrian crossing intention prediction. ADAPT processes four spatially aligned visual modalities, including RGB images, local depth maps, global semantic maps, and global depth maps, together with ego-vehicle speed, pedestrian bounding boxes, and skeleton pose information through five specialized modules: a weight-shared Swin Transformer V2 backbone for visual feature extraction, a Cross-Modality Guided Attention module for hierarchical visual fusion, a Mamba-based Motion Feature Encoding module for efficient temporal modeling, a Sparse Cross-Modal Attention module that selectively preserves the most informative inter-modal interactions, and a Vision Transformer-based Temporal Feature Fusion module for sequence-level prediction. Extensive experiments on the JAAD and PIE benchmark datasets demonstrate that ADAPT consistently outperforms existing state-of-the-art methods while maintaining low computational complexity. On JAAD, the proposed method achieves an AUC of 0.73 on JAADbeh and 0.85 on JAADall, while on PIE it achieves an accuracy of 0.92 and an AUC of 0.90. Furthermore, ADAPT performs inference in only 17.23 ms per sample, offering an effective balance between predictive accuracy and real-time deployment efficiency for intelligent transportation and autonomous driving applications.