Cross-Modal Learning

Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when temporally aligned audio and visual signals lack clear semantic correspondence. We propose to use text as a semantic anchor for audio-visual representation learning. To this end, we introduce a parameter-efficient adaptation framework built on frozen audio and visual encoders, centered on Text-Bridged Audio-Visual Adapter (TB-AVA), which enables text-mediated interaction between audio and visual streams. At the core of TB-AVA, Gated Semantic Modulation (GSM) selectively modulates feature channels based on text-inferred semantic relevance. We evaluate the proposed approach on multiple benchmarks, including AVE, AVS, and AVVP, where the proposed framework achieves state-of-the-art performance, demonstrating text as an effective semantic anchor for parameter-efficient fine-tuning (PEFT) in audio-visual learning.

Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectures that suffer from prohibitive computational overhead. In this paper, we present a systematic empirical analysis showing that decoupled MGNNs are substantially more efficient and scalable for large-scale graph learning. However, we identify a critical bottleneck in existing decoupled pipelines, namely modal conflict, which arises in both the propagation and aggregation stages. Specifically, independent multi-hop diffusion causes cross-modal semantic divergence during propagation, while naive fusion fails to align multi-hop feature trajectories during aggregation, jointly limiting effective representation learning. To address this challenge, we propose CAMPA, a Cross-modal Aligned Multimodal Propagation & Aggregation framework for decoupled multimodal graph learning. Concretely, CAMPA introduces a two-stage alignment mechanism: (1) cross-modal aligned propagation, which injects cross-modal similarity priors into message passing to preserve semantic consistency without additional parameter overhead; (2) trajectory aligned aggregation, which leverages trajectory-level self-attention and cross-attention to capture and align long-range dependencies across modalities and hops. Extensive experiments on diverse benchmark datasets and tasks demonstrate that CAMPA consistently outperforms strong coupled and decoupled baselines while preserving the efficiency advantages of the decoupled paradigm.

Audio-visual large language models (AVLLMs) have recently emerged as a powerful architecture capable of jointly reasoning over audio, visual, and textual modalities. In AVLLMs, the bidirectional interaction between audio and video modalities introduces intricate processing dynamics, necessitating a deeper understanding of their internal mechanisms. However, unlike extensively studied text-only or large vision language models, the internal workings of AVLLMs remain largely unexplored. In this paper, we focus on cross-modal information flow between audio and visual modalities in AVLLMs, investigating where information derived from one modality is encoded within the token representations of the other modality. Through an analysis of multiple recent AVLLMs, we uncover two common findings. First, AVLLMs primarily encode integrated audio-visual information in sink tokens. Second, sink tokens do not uniformly hold cross-modal information. Instead, a distinct subset of sink tokens, which we term cross-modal sink tokens, specializes in storing such information. Based on these findings, we further propose a simple training-free hallucination mitigation method by encouraging reliance on integrated cross-modal information within cross-modal sink tokens. Our code is available at https://github.com/kaistmm/crossmodal-hub.

Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cross-modal interference: information from one modality misguides the interpretation of another, thereby inducing hallucinations. We attribute this issue to uncontrolled cross-modal interactions during intermediate reasoning. To mitigate this, we propose Separate First, Fuse Later (SFFL), an audio-visual reasoning framework designed to reduce cross-modal interference. SFFL enforces modality-specific chain-of-thought reasoning, producing separate audio and visual reasoning traces and integrating evidence for answering. We construct modality-preference labels via a data pipeline under different modality input settings. We use these labels as an auxiliary reward in reinforcement learning to encourage a instance-dependent preference for modality cues when answering. We further introduce a modality-specific reasoning mechanism that preserves modality isolation during the separated reasoning stage while enabling full access to cross-modal information at the evidence fusion stage. Experiments demonstrate consistent improvements in both accuracy and robustness, yielding an average relative gain of 5.16% on general AVQA benchmarks and 11.17% on a cross-modal hallucination benchmark.

Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However, the modality heterogeneity, spatial misalignment, and the representation crisis of multiple modalities often limit the efficient of these cross-modal distillation methods. To address these limitations in existing approaches, we propose a hyperbolic constrained cross-modal distillation method for multimodal 3D object detection (HGC-Det). The proposed HGC-Det framework includes an image branch and a point cloud branch to extract semantic features from two different modalities. The point cloud branch comprises three core components: a 2D semantic-guided voxel optimization component (SGVO), a hyperbolic geometry constrained cross-modal feature transfer component (HFT), and a feature aggregation-based geometry optimization component (FAGO). Specifically, the SGVO component adaptively refines the spatial representation of the 3D branch by leveraging semantic cues from the image branch, thereby mitigating the issue of inadequate representation fusion. The HFT component exploits the intrinsic geometric properties of hyperbolic space to alleviate semantic loss during the fusion of high-dimensional image features and low-dimensional point cloud features. Finally, the FAGO compensates for potential spatial feature degradation introduced by the 2D semantic-guided voxel optimization component. Extensive experiments on indoor datasets (SUN RGB-D, ARKitScenes) and outdoor datasets (KITTI, nuScenes) demonstrate that our method achieves a better trade-off between detection accuracy and computational cost.

Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue refinement framework. MLCR organizes quality evidence at three levels: intra-modal representation, cross-modal interaction, and stage-wise aggregation. Specifically, the intra-modal decoupling encoder (IMDE) preserves modality identity while refining global temporal context and local frequency details. The cross-modal dynamic complementarity-aware retrieval (CMDCR) module retrieves incremental evidence conditioned on the evolving fused state and suppresses redundant responses. The stage-wise multimodal integration (SMI) block progressively accumulates intra-modal and cross-modal cues to refine the fused representation. Experiments on the Rhythmic Gymnastics and Fis-V datasets show that MLCR achieves the best or second-best performance in both Spearman correlation and prediction error, demonstrating its effectiveness and robustness.

Deep vision models degrade sharply in low-data regimes, particularly in medical imaging where labeled samples are scarce. We show this arises not merely from overfitting but from a geometric failure: finite-sample noise corrupts the embedding covariance, collapsing the eigengap and limiting the number of recoverable signal-bearing modes. We develop a spectral theory of finite-sample representation learning that quantifies the recoverable dimension K(N), the number of eigenmodes that can be stably estimated from N samples. Using perturbation theory and concentration bounds, we show that only modes with eigenvalues above the noise floor $\|\hatΣ - Σ\|_{\mathrm{op}} \sim \sqrt{D/N}$ are reliable, yielding a truncated Mahalanobis energy that governs classification performance. Under a power-law spectral model, this energy can be approximated by a truncated Riemann zeta function, linking eigenvalue decay to data efficiency and AUC. Within this framework, multimodal learning acts as spectral stabilization: vision-language models impose low-rank constraints that suppress noise-dominated directions and preserve the eigengap, increasing K(N) under data scarcity. Across MNIST and multi-disease neuroimaging, we show that multimodal training maintains more stable modes and improves class separation, even when unimodal models achieve comparable few-shot accuracy. These results identify spectral collapse as a fundamental bottleneck in low-data learning. We use truncated Mahalanobis energy and K(N) to diagnose encoder quality, and introduce zeta-based spectral filtering as a principled approach to improve data efficiency.

Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In this paper, we introduce \textbf{Omni-DeepSearch}, a benchmark for audio-driven omni-modal deep search. Given one or more audio clips and a related question, models must infer useful clues from audio, invoke text, image, and video search tools, and perform multi-hop reasoning to produce a short, objective, and verifiable answer. Omni-DeepSearch contains 640 samples across 15 fine-grained categories, covering four retrieval target modalities and four audio content types. A multi-stage filtering pipeline ensures audio dependence, retrieval necessity, visual modality necessity, and answer uniqueness. Experiments on recent closed-source and open-source omni-modal models show that this task remains highly challenging: the strongest evaluated model, Gemini-3-Pro, achieves only 43.44% average accuracy. Further analyses illustrate key bottlenecks in audio entity inference, query formulation, tool-use reliability, multi-hop retrieval, and cross-modal verification. These results highlight audio-driven omni-modal deep search as an important and underexplored direction for future multimodal agents.

Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research advances along two main paths: pre-training pseudo-label generators for fine-grained cross-modal semantic guidance, or refining AVVP model architectures to enhance audio-visual fusion. However, since audio and visual signals are typically unaligned, achieving accurate video parsing fundamentally relies on precise perception of uni-modal events. Yet these multi-modal focused strategies excessively emphasize multi-modal fusion while inadequately guiding and preserving uni-modal semantics, resulting in noisy pseudo-labels and sub-optimal video parsing performance. This paper proposes a novel framework that enhances uni-modal representations for both the pseudo-label generator and the AVVP model. Specifically, we introduce a similarity-based label migration approach to annotate pre-training data, thereby enabling the pseudo-label generator to better understand uni-modal events. We also employ a soft-constrained manner to refine modeling of uni-modal features in parallel with multi-modal fusion. These designs enable coordinated attention to both uni-modal and cross-modal representations, thus boosting the localization performance for events. Extensive experiments show that our method outperforms state-of-the-art methods in both pseudo-label and AVVP performance.

While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliability. Consolidating agent consistency requires distilling trial-error trajectories into reusable skills that preserve task-relevant invariants while discarding trajectory-specific noise. However, in multimodal settings, the key challenge is not only that useful invariants are distributed across vision and language information, but that different modalities support different kinds of reusable skill content: while some skills are verbalizable and interpretable, others reside in perceptual evidence beyond text. Text-only skills may lose perceptual cues, whereas storing text and perception naively introduces redundancy and noise. Existing inference-time methods, such as self-consistency, improve reliability through costly multi-sample decoding, while internalization strategies lack a way to separate verbalizable skill content from residual perceptual information. To address this, we introduce Conditional Multimodal Information Bottleneck (CMIB), a method for multimodal skill construction. CMIB begins with a joint bottleneck over multimodal skills and derives an exact sequential decomposition: (1) a text-stage bottleneck distilling interpretable skill cards, and (2) a conditional multimodal bottleneck compressing only residual information in perception that remains predictive beyond text. Unlike naive two-stream formulations, CMIB explicitly conditions the multimodal latent on the text skill, thus structurally reducing cross-modal redundancy and enabling independent control over textual and perceptual compression. We instantiate CMIB with a variational objective that makes its conditional decomposition tractable to optimize, yielding reusable multimodal skills that improve execution stability without incurring multi-sample inference overhead.

Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.

Health foundation models (FMs) learn useful representations from wearable sensors, but interpreting what they encode and transferring that knowledge across modalities after training remains difficult. We present a post-training framework that decomposes frozen embeddings into interpretable directions, referred to as symbols, and use these symbols to align the embedding spaces without retraining. We evaluate the framework on three FMs for photoplethysmography (PPG) and accelerometer data, independently pretrained on ~20M minutes of unlabeled data from ~172K participants, and analyzed on a held-out cohort of 30K subjects. We find that extracted symbols associate selectively with health conditions and physiological attributes, and these associations are partially shared across modalities and architectures. Cross-modal transfer via symbols retains more than 95% of in-domain performance, is nearly symmetric across domain directions, and saturates with limited paired data, together indicating that alignment recovers a shared low-dimensional subspace rich in physiological information. Overall, these results suggest that health FM embeddings contain an interpretable symbolic organization that is shared across modalities and supports cross-domain transfer without joint training.

Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distortion in image observations complicate cross-modal alignment and hinder stable fusion. Inspired by the fact that 2D images captured by cameras are representations of the 3D world, we recognize that the features learned from 2D and 3D segmentation share some common semantics, while other aspects remain modality-specific. This insight motivates a unified multimodal framework for joint 2D-3D semantic segmentation. We combine a SAM-based vision encoder with a SPTNet-based geometric encoder to extract complementary semantic and geometric representations. The resulting features from both modalities are explicitly decomposed into shared and private subspaces, where the shared components summarize semantic factors common to both domains, and the private components preserve properties that are unique to each modality. A lightweight attention-based fusion module aggregates the shared features into a consistent cross-modal representation, and a regularized training objective ensures both semantic alignment and subspace independence. Experiments on the SemanticKITTI and nuScenes benchmarks demonstrate consistent improvements in segmentation accuracy over representative multimodal baselines, accompanied by competitive computational efficiency. Cross-domain evaluation on nuScenes USA-Singapore shows stable performance under distribution shifts, demonstrating strong generalization. The implementation code is publicly available at: https://github.com/shuaizhang69/UniD-Shift.

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.

Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request physically inconsistent audio-video behavior. Each generation is evaluated along five dimensions: visual semantic adherence, audio semantic adherence, visual physical commonsense, audio physical commonsense, and cross-modal physical commonsense. Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts. We further introduce AV-Phys Agent, a ReAct-style evaluator that combines a multimodal language model with deterministic acoustic measurement tools, producing rankings that closely align with human ratings. Our results identify cross-modal physical consistency and transition-driven scene dynamics as key open challenges for joint audio-video generation.

Robust embodied navigation relies on complementary sensory cues. However, high-quality and well-aligned multi-modal data is often difficult to obtain in practice. Training a monolithic model is also challenging as rich multi-modal inputs induce complex representations and substantially enlarge the policy space. Cross-modal collaboration among lightweight modality-specialized agents offers a scalable paradigm. It enables flexible deployment and parallel execution, while preserving the strength of each modality. In this paper, we propose \textbf{CRONA}, a Multi-Agent Reinforcement Learning (MARL) framework for \textbf{Cro}ss-Modal \textbf{Na}vigation. CRONA improves collaboration by leveraging control-relevant auxiliary beliefs and a centralized multi-modal critic with global state. Experiments on visual-acoustic navigation tasks show that multi-agent methods significantly improve performance and efficiency over single-agent baselines. We find that homogeneous collaboration with limited modalities is sufficient for short-range navigation under salient cues; heterogeneous collaboration among agents with complementary modalities is generally efficient and effective; and navigation in large, complex environments requires both richer multi-modal perception and increased model capacity.

We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influence of feature $j$ on the attribution of feature $i$, denoted as meta-attribution $\varphi_{j \to i}(f)$, by treating the attribution method itself as a cooperative game and computing its Shapley value. Theoretically, we prove that attributions hierarchically decompose into meta-attributions, and establish these as directional extensions of existing interaction indices. Empirically, we demonstrate that the metagame delivers insights across diverse interpretability applications: (i) quantifying token interactions in instruction-tuned language models, (ii) explaining cross-modal similarity in vision-language encoders, and (iii) interpreting text-to-image concepts in multimodal diffusion transformers.

Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-modal settings and mainly focus on poisoning-based threats, leaving evasion-based threats underexplored. In this work, we first identify a cross-modal gradient mismatch under the multi-user promotion setting, where visual and textual perturbations are optimized in inconsistent directions due to the dominance of distinct user groups. This phenomenon dilutes the attack effectiveness and leads robust training to underestimate worst-case risks. To address this issue, we propose Untargeted Adversarial Training with Multimodal Coordination (UAT-MC). UAT-MC tackles the challenge of unknown targeted items in evasion-based attacks (as opposed to poisoning-based attacks) by treating all items as potential targets, and introduces a gradient alignment mechanism to explicitly correct this mismatch. This design ensures synchronized perturbations across modalities, thereby maximizing adversarial strength for robust training. Extensive experiments demonstrate that UAT-MC significantly improves robustness against promotion attacks while maintaining acceptable recommendation performance under the defense-accuracy trade-off. Code is available at https://github.com/gmXian/UAT-MC.

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based on non-semantic queries struggle to adapt to unlabeled tracking scenarios, making it difficult to learn reliable contextual cues. In this work, we propose a novel self-supervised tracking framework, named \textbf{\tracker}, which introduces a dual-modal context association mechanism that jointly leverages fine-grained semantic prompts and contextual noise to drive the model toward learning robust tracking representations. Adherent to the easy-to-hard learning principle, our contextual association mechanism operates based on two stages. During early training, instance patch tokens (prompts) are assigned to both forward and backward tracking branches to facilitate the acquisition of tracking knowledge. As training progresses, contextual noise is gradually injected into the model to perturb feature, encouraging the tracker to learn robust tracking representations in a more complex feature space. Thus, this novel contextual association mechanism enables our self-supervised model to learn high-quality tracking representations from unlabeled videos, while being applied exclusively during training to preserve efficient inference. Extensive experiments demonstrate the superiority of our method.

Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into the retrieval process. In this setting, vague queries often induce semantic ambiguity across videos, a challenge that is further exacerbated by the sparse temporal supervision within videos, which fails to provide sufficient matching evidence. To address this, we propose Holmes, a hierarchical evidential learning framework that aggregates multi-granular cross-modal evidence to quantify and model uncertainty explicitly. At the inter-video level, similarity scores are interpreted as evidential support and modeled via a Dirichlet distribution. Based on the proposed three-fold principle, we perform fine-grained query identification, which then guides query-adaptive calibrated learning. At the intra-video level, to accumulate denser evidence, we formulate a soft query-clip alignment via flexible optimal transport with an adaptive dustbin, which alleviates sparse temporal supervision while suppressing spurious local responses. Extensive experiments demonstrate that Holmes outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/ICML26-Holmes.

Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as a promising yet underexplored direction for enhancing DyTAG representation learning. However, existing methods typically rely on rigid modality partitions and one-shot fusion strategies, which limit their ability to capture the intrinsic and evolving dependencies between node semantics and interaction behaviors. To address these limitations, we propose \textbf{PRISM}, an iterative cross-modal posterior refinement framework for DyTAG representation learning. PRISM organizes DyTAG information into semantic and behavioral modalities, providing a more intrinsic alternative to carrier-level modality partitions. Instead of fusing the two modalities in a single step, PRISM learns a refinement trajectory that progressively transforms semantic priors into behavior-conditioned posterior states through cross-modal interaction with behavioral evidence. Extensive experiments on DTGB benchmark datasets show that PRISM achieves strong performance on temporal link prediction and destination node retrieval tasks. Further ablation studies validate the effectiveness of semantic--behavioral modeling and iterative posterior refinement.

Vehicle Re-identification (Re-ID) aims to retrieve the most similar image to a given query from images captured by non-overlapping cameras. Extending vehicle Re-ID from image-only queries to text-based queries enables retrieval in real-world scenarios where only a witness description of the target vehicle is available. In this paper, we propose PFCVR, a Part-level Fine-grained Cross-modal Vehicle Retrieval model for text-to-image vehicle re-identification. PFCVR constructs locally paired images and texts at the part level and introduces learnable part-query tokens that aggregate both part-specific and full-sentence context before aligning with visual part features. On top of this explicit local alignment, a bi-directional mask recovery module lets each modality reconstruct its masked content under the guidance of the other, implicitly bridging local correspondences into global feature alignment. Furthermore, we construct a new large-scale dataset called T2I-VeRW, which contains 14,668 images covering 1,796 vehicle identities with fine-grained part-level annotations. Experimental results on the T2I-VeRI dataset show that PFCVR achieves 29.2% Rank-1 accuracy, improving over the best competing method by +3.7% percentage points. On the newly proposed T2I-VeRW benchmark, PFCVR achieves 55.2% Rank-1 accuracy, outperforming a comprehensive set of recent state-of-the-art methods. Source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID

Emotion recognition from facial videos enables non-contact inference of human emotional states. Although facial expressions are widely used cues, they cannot fully reflect intrinsic affective states. Remote photoplethysmography (rPPG) provides complementary physiological information, but it is highly susceptible to noise and inter-subject variability, limiting generalization to unseen individuals. Existing multimodal methods combine facial and rPPG features, yet their fusion strategies often disrupt pretrained facial representations and lack explicit mechanisms to suppress subject-specific variations. To address these issues, we propose a subject-invariant cross-modal prompt-tuning framework for video-based emotion recognition. Specifically, rPPG waveforms are transformed into noise-robust time-frequency representations (TFRs), from which modality-complementary prompts are generated to modulate facial tokens within a frozen Vision Transformer (ViT). This design enables effective cross-modal interaction while preserving the generalizable facial representations learned by the pretrained backbone. In addition, we introduce a decoupled shared-specific adapter (DSSA) into each ViT layer to explicitly separate subject-shared and subject-specific components, thereby improving cross-subject generalization. Experiments on the MAHNOB-HCI and DEAP benchmarks demonstrate that the proposed method consistently outperforms strong baselines in both recognition accuracy and generalization ability, highlighting its effectiveness for video-based emotion recognition.

Text-based retrieval of Computer-Aided Design (CAD) models is a critical yet underexplored task for the reuse of legacy industrial designs. Existing CAD repositories are typically searched using filenames or directories, which limits the efficiency, scalability, and accuracy of design retrieval. In this paper, we formally introduce text-to-CAD retrieval as a new cross-modal retrieval task, aiming to retrieve semantically relevant CAD models from large-scale databases given natural language queries. Leveraging paired text-CAD annotations from the Text2CAD dataset, we establish a practical benchmark for this task. To achieve text-based retrieval, we propose a unified framework that learns multi-modal CAD embeddings from both procedural sequences and geometric point clouds. Specifically, a sequence encoder captures the construction logic of CAD models, while a point encoder extracts explicit geometric features. A text encoder is used to learn semantic representations of textual queries. During training, we introduce a novel feature decoder that reconstructs masked sequence features via cross-attention with text and point features, encouraging implicit multi-modal alignment. At inference time, we remove this auxiliary decoder to enable efficient retrieval using concatenated sequence-point features. Our framework serves as a strong baseline for text-to-CAD retrieval and lays the foundation for downstream CAD generation paradigms, such as retrieval-augmented generation. The source code will be released.

This companion paper reports the ICPR 2026 TVRID competition on privacy-aware top-view person re-identification. We present the competition setting, the released RGB-Depth dataset, and a summary of final results with descriptions of the top entries. TVRID contains 86 identities captured by four synchronized overhead Intel RealSense D455 cameras, with paired RGB/Depth streams and structured geometric variation across flat, ascent, descent, and oblique viewpoints. The evaluation protocol includes three tracks: RGB Re-ID, Depth Re-ID, and RGB$\leftrightarrow$Depth cross-modal retrieval. Submissions are ranked using mAP and CMC-1 under a unified server-side evaluation. The final results show a clear difficulty ordering (RGB $>$ Depth $>$ Cross-Modal), highlighting both the challenge of modality-constrained retrieval and the feasibility of strong performance with modality-invariant learning. By releasing the dataset at https://zenodo.org/records/17909410, the evaluation scripts at https://github.com/RaphaelDel/ICPR-TVRID, and the accompanying documentation, TVRID establishes a reproducible benchmark for top-view, depth-based, and cross-modal person re-id.

Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image-text pairs, models fail to show a fine-grained understanding of the combined semantics of these modalities. To address this issue we propose Hard Negative Captions (HNC): an automatically created dataset containing foiled hard negative captions for ITM training towards achieving fine-grained cross-modal comprehension in VL. Additionally, we provide a challenging manually-created test set for benchmarking models on a fine-grained cross-modal mismatch task with varying levels of compositional complexity. Our results show the effectiveness of training on HNC by improving the models' zero-shot capabilities in detecting mismatches on diagnostic tasks and performing robustly under noisy visual input scenarios. Also, we demonstrate that HNC models yield a comparable or better initialization for fine-tuning

Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucially, conflicts differ in resolvability: benign conflicts stem from missing, weak, or ambiguous cues and can be mitigated by cross-modal calibration, while severe conflicts arise from intrinsically contradictory (e.g., sarcasm) or misleading signals, for which forced fusion may amplify errors. Recognizing this, we propose Dual-Path Conflict Resolution (DCR), a unified framework that learns when to fuse and when to drop modalities. Path I (Affective Fusion Distiller, AFD) performs reverse distillation from audio/visual teachers to a textual student using temporally weighted class evidence, thereby enhancing representation-level calibration and improving fusion when alignment is beneficial. Path II (Affective Discernment Agent, ADA) formulates MER as a contextual bandit that selects among fusion and unimodal predictions based on a dual-view state and a calibration-aware reward, enabling decision-level arbitration under irreconcilable conflicts without requiring per-modality reliability labels. By taking into account the full multimodal context and coupling soft calibration with hard arbitration, DCR reconciles conflicts that can be aligned while bypassing misleading modalities when fusion is harmful. Across five benchmarks covering both dialogue-level and clip-level MER, DCR consistently outperforms competitive baselines or achieves highly competitive results. Further ablations, conflict-specific subset evaluation, and modality-selection analysis verify that AFD and ADA are complementary and jointly improve robust conflict-aware emotion recognition.

Deep neural networks enriched with structural information have been widely employed for facial expression recognition tasks. However, these methods often depend on hierarchical information rather than face property to finish expression recognition. In this paper, we propose a cross-modal network with strong biological and structural information for facial expression recognition (CMNet). CMNet can respectively learn expression information via face symmetry on a whole face, left and right half faces to extract complementary facial features. To prevent negative effect of biological and structural information fusion, a salient facial information refinement module can obtain salient facial expression information to improve stability of an obtained facial expression classifier. To reduce reliance on unilateral facial features, a half-face alignment optimization mechanism is designed to align obtained expression information of learned left and right half faces. Our experimental results demonstrate that CMNet outperforms several novel methods, i.e., SCN and LAENet-SA for facial expression recognition. Codes can be obtained at https://github.com/hellloxiaotian/CMNet.

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.

Modern IoT and sensor networks generate vast amounts of data, posing significant challenges for storage, transmission, and real-time processing. Traditional approaches, such as compressive sensing and machine learning-based compression, often suffer from computational inefficiencies and irreversible data loss. This paper introduces Information Density as a quantitative metric to support sensor deployment and enable AI-driven virtual sensing. We propose a framework that leverages spatial, temporal and inter-modal correlations among sensor signals to perform sensing tasks even in the absence of physical sensors. Two complementary measures: (i) Phase in Eigen Space and (ii) Mutual Information, are developed to quantify and assess information density, enabling the selection of optimal sensor configurations across both intra-modality and cross-modality scenarios. Validated using real-world data from Madrid's smart city infrastructure, this framework demonstrates the feasibility of replacing physical sensors with virtual ones under bounded error conditions (e.g., achieving $<3.21\%$ mean error with a single sensor). The results highlight the potential for scalable and energy-efficient sensing systems in smart environments.

Video Temporal Grounding (VTG) faces a cross-modal semantic gap that often leads to background features being incorrectly aligned with the query, while directly matching the query to moments results in insufficient discriminability and consistency of temporal semantics. To address this issue, we propose MLLM-Assisted Semantic-Relational Consistent Alignment (MASRA), a training-time MLLM-based optimization framework for VTG. MASRA leverages an MLLM during training to produce two forms of textual priors, namely event-level descriptions with temporal spans and clip-level captions, and instantiates two MLLM-assisted alignments. Event Semantic Temporal Alignment (ESTA) aligns temporal context with event semantics to explicitly strengthen the correspondence between semantics and temporal events and improve span-level separability. Local Relational Consistency Alignment (LRCA) constructs a textual relation matrix derived from clip-level captions and aligns it with the temporal feature similarity matrix in the model, enhancing temporal consistency while capturing local structural information. MASRA includes two simple supporting modules, semantic-guided enhancement and second-order relational attention, to better utilize the learned semantic context and relational structure. Moreover, we introduce Decoupled Alignment Interaction (DAI) with a context-aware codebook to adaptively absorb query-irrelevant semantics and alleviate the cross-modal gap. The MLLM is only invoked during training and is not used at inference. Extensive experiments show that MASRA outperforms existing methods, and ablation studies validate its effectiveness.

Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that existing unlearning strategies tend to apply uniform parameter selection and editing across all graph neural network (GNN) layers, which is especially harmful for multimodal graphs where high-dimensional input projections encode dominant cross-modal knowledge. As a result, over-editing these sensitive layers often leads to catastrophic utility degradation after forgetting, undermining both stable learning and effective privacy protection. To address this gap, we propose FDQ, a Feature-Dimension Aware Quantile framework for multimodal graph unlearning. FDQ adaptively identifies high-dimensional input projection layers and applies more conservative, FDQ-guided quantile thresholds when constructing suppression sets, while keeping the underlying importance estimation mechanism unchanged. FDQ is seamlessly integrated with diagonal sensitivity-based parameter importance analysis to enable efficient node and edge unlearning under general forget requests. Through extensive experiments on Ele-Fashion and Goodreads-NC, we demonstrate that FDQ consistently achieves strong utility preservation while maintaining effective forgetting against membership inference attacks. Overall, FDQ offers a principled and robust solution for privacy-aware unlearning in high-dimensional multimodal graph systems.

Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While several datasets exist for natural images and high-resolution optical remote sensing imagery, the availability of captioning datasets for multimodal satellite data remains limited, particularly for SAR imagery and medium-resolution sensors. We introduce Sentinel2Cap, a human-annotated multimodal captioning dataset containing Sentinel-1 SAR and Sentinel-2 multi-spectral image patches at 10 m and 20 m spatial resolution with diverse land cover compositions. Captions are created manually and carefully validated to ensure both semantic accuracy and linguistic quality. To evaluate Sentinel2Cap, we perform a zero-shot captioning using the Qwen3-VL-8B-Instruct model across three image modalities: RGB, multi-spectral, and SAR pseudo-RGB representations. Results show that RGB images achieve the highest captioning performance, while SAR images remain more challenging for vision-language models. Providing modality-specific contextual prompts consistently improves performance across all metrics. These findings highlight both the challenges of multimodal remote sensing image captioning and the potential value of human-annotated datasets for advancing research in cross-modal scene understanding. All the material is publicly avaiable.

Long-term autonomy requires robust navigation in environments subject to dynamic and static changes, as well as adverse weather conditions. Teach-and-Repeat (T&R) navigation offers a reliable and cost-effective solution by avoiding the need for consistent global mapping; however, existing T&R systems lack a systematic solution to tackle various environmental variations such as weather degradation, ephemeral dynamics, and structural changes. This work proposes LTR$^2$, the first cross-modal, cross-platform LiDAR-Teach-and-Radar-Repeat system that systematically addresses these challenges. LTR$^2$ leverages LiDAR during the teaching phase to capture precise structural information under normal conditions and utilizes 4D millimeter-wave radar during the repeating phase for robust operation under environmental degradations. To align sparse and noisy forward-looking 4D radar with dense and accurate omnidirectional 3D LiDAR data, we introduce a Cross-Modal Registration (CMR) network that jointly exploits Doppler-based motion priors and the physical laws governing LiDAR intensity and radar power density. Furthermore, we propose an adaptive fine-tuning strategy that incrementally updates the CMR network based on localization errors, enabling long-term adaptability to static environmental changes without ground-truth labels. We demonstrate that the proposed CMR network achieves state-of-the-art cross-modal registration performance on the open-access dataset. Then we validate LTR$^2$ across three robot platforms over a large-scale, long-term deployment (40+ km over 6 months), including challenging conditions such as nighttime smoke. Experimental results and ablation studies demonstrate centimeter-level accuracy and strong robustness against diverse environmental disturbances, significantly outperforming existing approaches.

Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. Despite recent progress, existing methods rely heavily on costly frame-level spatial annotations and cross-view identity supervision. To reduce such reliance, we explore CRMOT under weak supervision by leveraging the capabilities of foundation models. However, our empirical study shows that directly applying foundation models such as SAM2 and SAM3, even with task-specific modifications, fails to accurately understand referring expressions and maintain consistent identities across views. Yet, they remain effective at producing reliable object tracklets that can serve as pseudo supervision. We therefore repurpose foundation models as pseudo-label generators and propose a two-stage framework for weakly supervised CRMOT, using only object category labels as coarse-grained supervision. In the first stage, we design an Affinity-guided Cross-view Re-prompting strategy to refine and associate SAM3-generated tracklets across cameras, producing reliable cross-view pseudo labels for subsequent training. In the second stage, we introduce ViewSAM, a CRMOT model built upon SAM2 that explicitly models view-aware cross-modal semantics. By formulating view-induced variations as learnable conditions, ViewSAM bridges the gap between view-variant visual observations and view-invariant textual expressions, enabling robust cross-view referring tracking with only approximately 10% additional parameters. Extensive experiments demonstrate that ViewSAM achieves SOTA performance under weak supervision and remains competitive with fully supervised methods.

Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ separate encoders for each modality and a fusion module, training the system end-to-end by optimizing on the fused features. In this paper, we identify that such joint optimization causes encoders to exploit cross-modal co-occurrences, statistical relationships between modalities that arise from source-specific recording conditions, rather than learning domain-invariant features. We term this failure mode Fusion Overfitting. To address this, we propose Modality-Entropy Regularization for Domain Generalization (MER-DG), which maximizes the entropy of each encoder's feature distribution to preserve feature diversity. MER-DG is architecture-agnostic and integrates into existing multimodal frameworks as an additive loss term. Extensive experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of approximately 5% over standard fusion and approximately 2% over state-of-the-art methods.

Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusion bridges are effective for this task. However, most existing approaches rely on fully paired datasets, thereby imposing a single data-driven constraint. We propose a diffusion-bridge framework that characterizes the space of admissible solutions and restricts it via alignment constraints, treating paired supervision as an optional heuristic rather than a prerequisite. We validate our method on synthetic and real modality translation benchmarks across unpaired, semi-paired, and paired regimes, showing consistent performance across supervision levels. Notably, \textbf{it achieves near fully-paired quality with a substantial relaxation in pairing requirements, and remaining applicable in the unpaired regime}. These results highlight diffusion bridges as a flexible foundation for modality translation beyond fully paired data.

Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.

Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, embeddings can reflect modality more than meaning, so examples cluster by input type even when the underlying content matches. Second, the paired supervision used to train these spaces is often noisy. When we blend many heterogeneous, human-labeled datasets, these issues reinforce each other and degrade cross-modal retrieval. We present a framework that improves alignment by acting on both the training pairs and the embedding model. Symmetric Nucleus Subsampling (SNS) refines training pairs by trimming raw inputs and annotations to the portions that best support each other. Expert Embedding Engine (EEE) combines complementary embedding experts using a learned projection network, together with a bias-aware objective that reduces modality-driven separation in the embedding space. We demonstrate that this approach collapses the modality gap by over 90% on average vs base embedding experts and is a strong data curator, with datablends from our method outperforming stratified sampling and traditional curation baselines in downstream model performance.

Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, most existing self supervised learning methods treat these signals as interchangeable views, overlooking the directional temporal dynamics that link them. A canonical example is the relationship between electrocardiography (ECG), which captures the electrical activation initiating each heartbeat, and photoplethysmography (PPG), which records the resulting peripheral pulse delayed by vascular dynamics. To capture this structured relationship, we introduce xMAE, a biosignal pretraining framework that leverages masked cross modal reconstruction across temporally ordered biosignals as a training time constraint to encourage physiologically meaningful timing structure in the learned representations. We show that pretraining with xMAE yields representations that outperform both unimodal and multimodal baselines on 15 of 19 downstream tasks, including cardiovascular outcome prediction, abnormal laboratory test detection, sleep staging, and demographic inference, while generalizing across devices, body locations, and acquisition settings. Further analysis suggests that the ECG PPG timing structure is reflected in the learned PPG representations. More broadly, xMAE demonstrates the effectiveness of incorporating temporal structure into multimodal pretraining when signals observe different stages of a shared underlying process. Code is available at https://github.com/hzhou3/xMAE.

Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles forgotten knowledge across both modalities and client gradient subspaces, hindering federated unlearning. Previous federated unlearning approaches neither sever the cross-modal reconstruction channel mediated by bilinear coupling nor separate forget-exclusive update directions from those shared with retained clients. We identify an Anchor Principle for federated multimodal contrastive unlearning: forgotten alignments persist through three residual anchors arising from bilinear cross-modal coupling, principal-angle subspace entanglement, and continued federated updates. At the modality level, we show that bilateral displacement of both visual and language branches closes the cross-modal reconstruction channel. Correspondingly, our method addresses subspace entanglement through Cosine--Sine decomposition of client-update subspaces, isolating forget-exclusive directions from retain support. Moreover, we propose a direction-selective Forget Lock that bounds residual drift across rounds. Combining these strategies, we present EASE, an Entanglement-Aware Subspace Excision framework that closes all three anchor channels under a unified design. EASE demonstrates consistent superiority across multiple datasets and unlearning scenarios, for instance, matching the retrain reference to within 0.2 and 4.2 R@1 points on the forget and retain sides under client unlearning on Flickr30K with CLIP-B/32.

Automated pediatric electrocardiogram (ECG) interpretation remains challenging because developmental differences in heart rate, intervals, and waveforms limit the transferability of models trained mainly on adult data, while expert-labeled pediatric ECG cohorts are scarce. We propose PEACE (Pediatric-Adult ECG Alignment via Cross-modal Enhancement), an adult-to-pediatric ECG transfer framework pretrained on MIMIC-IV ECGs and adapted to pediatric targets. PEACE integrates label-specific bidirectional contrastive learning (LSBC) to align ECG representations with diagnostic semantics and curriculum adaptive fusion (CAF) to stabilize optimization under limited pediatric supervision. Label-conditioned short text descriptors provide auxiliary semantic supervision during training, whereas inference requires ECG signals only. On ZZU-pECG, PEACE achieves macro-average AUCs of 59.39%, 81.74%, and 91.56% under zero-shot, 50-shot, and full fine-tuning settings, respectively, outperforming ECG-only, multimodal, and generic domain adaptation baselines including DANN and MMD. On PTB-XL, it reaches 96.90% macro-average AUC after full fine-tuning over nine harmonized labels with nonzero mapped incidence. Gradient-based attention maps show increased saliency around QRS voltage and morphology regions for chamber-related RVH and around QRS-to-T/repolarization intervals for LQTS, broadly consistent with ECG regions commonly inspected during routine interpretation. These results suggest that adult-scale ECG pretraining coupled with rhythm, morphology, and ST-T repolarization semantic descriptors improves transferable pediatric diagnosis under label scarcity while preserving clinically interpretable waveform focus.

The proliferation of advanced AI video synthesis techniques poses an unprecedented challenge to digital video authenticity. Existing AI-generated video (AIGV) detection methods primarily focus on uni-modal or spatiotemporal artifacts, but they overlook the rich cues within the visual-textual cross-modal space, especially the temporal stability of semantic alignment. In this work, we identify a distinctive fingerprint in AIGVs, termed cross-modal temporal artifact (CMTA). Unlike real videos that exhibit natural temporal fluctuations in cross-modal alignment due to semantic variations, AIGVs display unnaturally stable semantic trajectories governed by given input prompts. To bridge this gap, we propose the CMTA framework, a cross-modal detection approach that captures these unique temporal artifacts through joint cross-modal embedding and multi-grained temporal modeling. Specifically, CMTA leverages BLIP to generate frame-level image captions and utilizes CLIP to extract corresponding visual-textual representations. A coarse-grained temporal modeling branch is then designed to characterize temporal fluctuations in cross-modal alignment with a GRU. In parallel, a fine-grained branch is constructed to capture intricate inter-frame variations from integrated visual-textual features with a Transformer encoder. Extensive experiments on 40 subsets across four large-scale datasets, including GenVideo, EvalCrafter, VideoPhy, and VidProM, validate that our approach sets a new state-of-the-art while exhibiting superior cross-generator generalization. Code and models of CMTA will be released at https://github.com/hwang-cs-ime/CMTA

In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.

Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design.

Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a cross-modal framework that learns an RGB- and Event-Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models. Instead of task-specific training, we leverage low-rank adaptation (LoRA) to bridge the modality gap, effectively unlocking the geometric and semantic priors of frozen RGB backbones for asynchronous event streams. We demonstrate that REALM effectively maps events into the ViT-based foundation latent space. Our method performs downstream tasks, such as depth estimation and semantic segmentation, by simply transferring linear heads trained on the RGB teacher. Most significantly, REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures. Code and models are available at https://papers.starslab.ca/realm/.

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pass reasoning fragility. To address these, we propose Retrieval-Augmented Multi-modal Multi-agent Stance Detection (MM-StanceDet), a novel multi-agent framework integrating Retrieval Augmentation for contextual grounding, specialized Multimodal Analysis agents for nuanced interpretation, a Reasoning-Enhanced Debate stage for exploring perspectives, and Self-Reflection for robust adjudication. Extensive experiments on five datasets demonstrate MM-StanceDet significantly outperforms state-of-the-art baselines, validating the efficacy of its multi-agent architecture and structured reasoning stages in addressing complex multimodal stance challenges.

The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a practical threat for purposes such as information retrieval and automatic evaluation metrics. In particular, since cross-modal similarity between text and images cannot be calculated by direct comparisons, such as string matching, cross-modal encoders that project different modalities into a shared space are helpful for various cross-modal applications, and thus, the existence of hubs may pose practical threats. To reveal the vulnerabilities of cross-modal encoders, we propose a method for identifying the hub embedding and its corresponding hub text. Experiments on image captioning evaluation in MSCOCO and nocaps along with image-to-text retrieval tasks in MSCOCO and Flickr30k showed that our method can identify a single hub text that unreasonably achieves comparable or higher similarity scores than human-written reference captions in many images, thereby revealing the vulnerabilities in cross-modal encoders.

Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT image semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and severe semantic confusion among fine-grained ground objects under top-down aerial views. To address these issues, we propose a Graph-based Semantic Calibration Network (GSCNet) for unaligned UAV RGBT image semantic segmentation. Specifically, we design a Feature Decoupling and Alignment Module (FDAM) that decouples each modality into shared structural and private perceptual components and performs deformable alignment in the shared subspace, enabling robust spatial correction with reduced modality appearance interference. Moreover, we propose a Semantic Graph Calibration Module (SGCM) that explicitly encodes the hierarchical taxonomy and co-occurrence regularities among ground-object categories in UAV scenes into a structured category graph, and incorporates these priors into graph-attention reasoning to calibrate predictions of visually similar and rare categories. In addition, we construct the Unaligned RGB-Thermal Fine-grained (URTF) benchmark, to the best of our knowledge, the largest and most fine-grained benchmark for unaligned UAV RGBT image semantic segmentation, containing over 25,000 image pairs across 61 semantic categories with realistic cross-modal misalignment. Extensive experiments on URTF demonstrate that GSCNet significantly outperforms state-of-the-art methods, with notable gains on fine-grained categories. The dataset is available at https://github.com/mmic-lcl/Datasets-and-benchmark-code.

Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required for clinical integration. Standard feature attribution methods are limited by the inherent difficulty in mapping abstract waveform fluctuations to physical anatomical pathologies. To resolve this, we propose a cross-modal method that projects feature attributions from high-performance 12-lead ECG models onto the CineECG 3D anatomical space. Our study reveals that while models trained directly on CineECG signals suffer from reduced accuracy and incoherent attributions, the proposed mapping mechanism effectively recovers clinically relevant feature rankings. Validated against a ground-truth dataset of 20 cases annotated by domain experts, the mapped explanations yield a Dice score of 0.56, significantly outperforming the 0.47 baseline of standard 12-lead attributions. These findings indicate that cross-modal averaging mapping effectively filters attribution instability and improves the localization of pathological features, combining the diagnostic expressiveness of standard ECG with the intuitive clarity of anatomical visualization.

Predicting social media popularity requires understanding both the intrinsic appeal of content and the external context that determines how it is exposed to users. Existing methods focus on content signals but do not separate them from exposure-related patterns, which causes the learned representations to absorb platform-specific visibility effects and weakens both interpretability and cross-platform transfer. This paper introduces OmniTrend, a unified framework that models popularity as the joint outcome of content attractiveness and contextual exposure. The content module learns cross-modal representations from visual, audio, and textual cues to quantify intrinsic appeal, while the context module estimates exposure from exogenous signals such as posting time, author activity, topical trends, and retrieval-based neighborhood statistics. OmniTrend learns separate predictors for content attractiveness and contextual exposure and integrates them in the final popularity estimate, which makes the role of each factor explicit and supports robust transfer across image and video platforms.

Generalized Category Discovery (GCD) aims to categorize unlabelled instances from both known and unknown classes by transferring knowledge from labelled data of known classes. Existing methods assume all data comes from a single domain, yet real-world unlabelled data often exhibits domain shifts alongside semantic shifts. We study GCD under domain shifts and propose three frameworks that adapt foundation models, ranging from self-supervised vision models to vision-language models. (i) HiLo disentangles domain and semantic features through multi-level feature extraction and mutual information minimization, combined with PatchMix augmentation and curriculum sampling. (ii) HLPrompt extends HiLo with semantic-aware spatial prompt tuning to suppress background and domain noise. (iii) VLPrompt leverages vision-language models via factorized textual prompts and cross-modal consistency regularization. The three methods share core design principles while operating on different foundation backbones, making them suitable for different deployment scenarios. Extensive experiments on synthetic corruptions and real-world multi-domain shifts demonstrate consistent improvements over strong baselines. Project page: https://visual-ai.github.io/hilo/

Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus on sample-level objectives via contrastive learning while overlooking the crucial subject-level semantics. This limitation hinders the model's ability to group semantically coherent subjects in complex multimodal queries, manifesting as semantic alignment deviation--where models fail to accurately localize salient text-referred regions in visual content. Moreover, without explicit guidance to model salient visual subjects, LMMs tend to over-rely on textual cues, resulting in visual modality neglect and suboptimal utilization of visual knowledge. To this end, we propose Salient Subject-Aware Multimodal Embedding (SSA-ME), a novel framework designed to enhance fine-grained representation learning through saliency-aware modeling. SSA-ME leverages LMMs and visual experts to identify and emphasize salient visual concepts in image-text pairs, and introduces a saliency-guided objective to better align cross-modal attention with semantically meaningful regions. Additionally, a feature regeneration module recalibrates visual features based on the derived saliency maps, ensuring a balanced and semantically coherent integration across modalities. Extensive experiments show that our method achieves state-of-the-art performance on the MMEB benchmark, demonstrating that incorporating subject-level modeling substantially improves multimodal retrieval. Comprehensive qualitative analyses further illustrate the interpretability and effectiveness of our approach.

Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely aligned frames of the same individual with identical speech but different expressions, which impedes direct supervision for emotional manipulation. While current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision, their direct application is limited. To this end, we propose a Personalized Cross-Modal Emotional Correlation Learning (PCMECL) algorithm that refines VLM-based supervision through two major improvements. First, standard VLMs rely on a single generic prompt for each emotion, failing to capture expressive variations among individuals. PCMECL addresses this limitation by conditioning on individual visual information to learn personalized prompts, thereby establishing more fine-grained visual-semantic correlations. Second, even with personalization, inherent discrepancies persist between the visual and semantic feature distributions. To bridge this modality gap, PCMECL employs feature differencing to correlate the modalities, providing more precisely aligned supervision by matching the change in visual features to the change in semantic features. As a plug-and-play module, PCMECL can be seamlessly integrated into existing SPFEM models. Extensive experiments across various datasets demonstrate the superior efficacy of our algorithm.

Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can sharpen the fused posterior while increasing error, because an unreliable modality may still dominate fusion. We study this failure mode through a majorization view of multimodal posteriors and cast adaptation as a constrained de-mixing problem on the fused prediction. Based on this view, we propose MG-MTTA, which keeps the backbone frozen and updates only a lightweight gate or adapter. The objective combines fused-posterior entropy minimization with a reliability-aware gate prior built from anchor-based modality consistency and cross-modal conflict. Our analysis gives conditions under which entropy reduction preserves the correct ranking and a threshold that characterizes modality-dominance failure. On the ImageNet-based benchmark, MG-MTTA improves top-1 accuracy from 57.97 to 66.51 under semantics-preserving textual shift and from 21.68 to 26.27 under joint visual-textual shift, while remaining competitive in the visual-only benchmark. These results show that multimodal test-time adaptation should control modality reliability, not just prediction entropy.

Accurate whole-cell and nuclear segmentation is essential for precision pathology and spatial omics, yet routine hematoxylin and eosin (H&E) staining provides limited cytoplasmic contrast, restricting analyses to nuclei. Multiplex immunofluorescence (mIF) facilitates precise whole-cell delineation but remains constrained by cost and accessibility. We introduce VitaminP, a cross-modal learning framework enabling whole cell segmentation from H&E images. By learning from paired H&E-mIF data, VitaminP transfers molecular boundary information from mIF to overcome cytoplasmic contrast in H&E, establishing cross-modal supervision as a general strategy for recovering missing biological structure. We train VitaminP on 14 public datasets covering 34 cancer types and over 7 million instances, integrating publicly available labels with extensive annotations generated in this study, forming one of the largest resources for segmentation. VitaminP outperforms four state-of-the-art methods and generalizes to unseen datasets, including an in-house dataset spanning 24 rare cancer types. We further developed VitaminPScope, an open-source platform providing an interface for scalable inference and enabling broad adoption.

Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating high-level semantics and low-level details in a fully entangled manner. This is suboptimal for talking head synthesis: while audio and facial motion are semantically correlated, their low-level realizations (acoustic signals and visual textures) follow distinct rendering processes. Enforcing joint modeling across all levels causes unnecessary entanglement and reduces efficiency. We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone, while low-level refinement uses modality-specific decoders. A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space. Two lightweight diffusion transformer heads decode the hidden states into frame-level audio and video latents. Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality, achieving stronger cross-modal consistency than cascaded pipelines.

Analog circuit design relies heavily on reusing existing intellectual property (IP), yet searching across heterogeneous representations such as SPICE netlists, schematics, and functional descriptions remains challenging. Existing methods are largely limited to exact matching within a single modality, failing to capture cross-modal semantic relationships. To bridge this gap, we present AnalogRetriever, a unified tri-modal retrieval framework for analog circuit search. We first build a high-quality dataset on top of Masala-CHAI through a two-stage repair pipeline that raises the netlist compile rate from 22% to 100%. Built on this foundation, AnalogRetriever encodes schematics and descriptions with a vision-language model and netlists with a port-aware relational graph convolutional network, mapping all three modalities into a shared embedding space via curriculum contrastive learning. Experiments show that AnalogRetriever achieves an average Recall@1 of 75.2% across all six cross-modal retrieval directions, significantly outperforming existing baselines. When integrated into the AnalogCoder agentic framework as a retrieval-augmented generation module, it consistently improves functional pass rates and enables previously unsolved tasks to be completed. Our code and dataset will be released.

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings.

Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity, a single global model is often insufficient to capture both shared cross-modal knowledge and client-specific characteristics. We propose RCSR, a personalization-friendly federated framework that integrates prototype anchoring, retrieval-centric semantic routing, and optional client-specific adapters. Built on a frozen CLIP backbone, RCSR leverages lightweight shared adapters for global knowledge transfer while supporting efficient local personalization. Prototype anchoring helps unimodal clients align with global cross-modal semantics, and a server-side semantic router adaptively assigns aggregation weights based on retrieval consistency to mitigate alignment drift during heterogeneous updates. Extensive experiments on MS-COCO, Flickr30K, and other benchmarks show that RCSR consistently improves global retrieval accuracy and training stability, while further enhancing client-level retrieval performance, especially for clients with incomplete modalities. Code is available at https://github.com/RezinChow/RCSR-Retrieval-Centric-Semantic-Routing.