Multimodal Learning

Ask about this topic

Overview

Multimodal learning asks how information from different sources can be combined to improve tasks such as diagnosis, retrieval, forecasting, and robot perception. Common approaches include feature fusion and cross-attention, contrastive alignment, self-supervised pretraining, and mixture-of-experts models that balance shared information with modality-specific cues. Foundation models increasingly support understanding and generation across several modalities, while domain-specific systems use paired or partially paired data and may use extra inputs during training even when they are unavailable at deployment. A central tension is that modalities can complement one another but can also be missing, noisy, misaligned, or unevenly used, so research focuses on robust fusion and evaluations that test whether models truly rely on the relevant evidence.

Latest papers

CardsList

338 papers38 papers in the last four weeks, down 5% on the four weeks before. 0.2% of all new papers.

Aug 24, 2026

CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery

End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance, where one branch dominates gradient-based optimization; (ii) unstable gating, where noisy confidence cues induce erratic modality selection; and (iii) fusion interference, where modality-specific gradients conflict at the shared fusion layer. We propose CAT-GS (Calibrated, Adaptive, Thresholded Gating with Fusion Surgery), a neural dynamics-based optimization controller for intelligent computing applications. CAT-GS operates during backpropagation without modifying model architectures, fusion modules, or task losses. Through calibration of teacher-derived reliability via temperature scaling and EMA smoothing, CAT-GS stabilizes neural dynamics using a margin-thresholded policy to switch between warm-up dropout, weak-modality prioritization, and weak-biased blending, stabilizes gradient magnitudes under aggressive gating via capped gradient-budget renormalization, and applies fusion-only PCGrad to reduce destructive cross-modal interference at the primary shared bottleneck. We evaluate CAT-GS on audio--visual multimodal pattern recognition benchmarks (CREMA-D, AV-MNIST, and VGGSound), a tri-modal setting (UR-FUNNY), controlled synthetic data (CG-MNIST), and additional cross-domain benchmarks (AVE and CMU-MOSI). CAT-GS improves or matches fused multimodal accuracy against strong imbalance-aware baselines (including OGM-GE, G2^2D, and UMT) across settings, and yields smoother gating behavior with fewer conflicting fusion gradients.

Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +3

Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh

Multimodal UnderstandingCross-Modal LearningModality ImbalanceGradient InterferenceMultimodal OptimizationMultimodal Fusion+2
AskPDF
Aug 22, 2026

Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients

Accurate assessment of patients in intensive care units (ICUs) is essential for timely clinical intervention and improved patient outcomes. Multimodal electronic health records (EHRs), including structured physiological time series and longitudinal clinical notes, provide complementary information for critical care prediction. However, in real-world clinical settings, individual modalities may be partially observed or entirely unavailable, resulting in substantial performance degradation for existing multimodal models. To address this challenge, we propose a multimodal prompt-learning framework for robust clinical prediction under diverse missing-modality scenarios. The proposed framework introduces four complementary types of prompts: generative prompts, missing-signal prompts, missing-type prompts, and temporal prompts. Generative prompts construct surrogate latent representations for unavailable modalities, while missing-signal prompts distinguish observed representations from generated ones. Missing-type prompts condition the model on different modality-availability configurations, whereas temporal prompts perform condition-specific aggregation over temporally encoded clinical sequences. Together, these prompts enable the model to capture missingness-aware intramodal dependencies and cross-modal interactions within a unified architecture. Extensive experiments demonstrate that our method outperforms existing approaches across evaluation metrics on two missingness settings. Ablation and robustness analyses further verify the complementary contributions of the four prompt types and the effectiveness of the proposed framework for clinical prediction from incomplete multimodal EHR data.

Yixin Yang, Yueyang Sun, Weichen Liu +2

Faculty of Engineering, Shenzhen MSU-BIT University · International School, Beijing University of Posts and Telecommunications · School of Computer Science and Engineering, Southeast University +1

Missing-Modality LearningMultimodal LearningClinical Outcome PredictionLongitudinal EHR ModelingMultimodal Fusion
AskPDF
Aug 20, 2026

Contrastive Mixed Prompt Learning for Incomplete Multimodal Sentiment Analysis with Unseen Modality Combination

Incomplete multimodal sentiment analysis has garnered significant attention in recent years. Existing approaches typically assume that data is missing at random or are designed specifically for certain missing patterns, ignoring the modality combination inconsistency between training and testing phases. However, in real-world scenarios, the testing phase often encounters modal combinations that were not present during the training phase, which leads to insufficient generalization capabilities and unstable performance. In this paper, we introduce the problem of Incomplete Multimodal Sentiment Analysis with Unseen Modality Combinations (IMSAUMC), aiming to enhance model generalization for unseen modality combinations. To address this challenge, we propose the model named C\textbf{C}ontrastive M\textbf{M}ixed P\textbf{P}rompt L\textbf{L}earning (CMPL\textsf{CMPL}) for IMSAUMC. It introduces a label-guided contrastive feature learning mechanism to learn robust and discriminative cross-modal representations. Additionally, we design modality-combination prompts with a soft router to facilitate better learning of various modality combinations. Furthermore, we introduce three prompt contrastive learning strategies, which enable effective learning of prompts corresponding to unseen modality combinations, thereby significantly strengthening the model's generalization capabilities in diverse testing scenarios. Extensive experiments on three widely used datasets demonstrate that CMPL\textsf{CMPL} achieves more than a 5% improvement in accuracy compared to state-of-the-art approaches.

Kaixin Xu, NaiJin Liu, Yulin Kang +8

School of Software Technology, Zhejiang University · Beijing WuZi University · Ant Group +3

Multimodal Sentiment AnalysisMultimodal LearningMissing-Modality LearningPrompt LearningMultimodal Contrastive Learning
AskPDF
Aug 20, 2026

MUST-PET: MUltimodal Self-supervised learning across Tracers for whole-body PET/CT-based lesion segmentation

Deep learning-based whole-body PET-CT lesion segmentation can support cancer staging, treatment planning, and response assessment, but generalization is limited by scarce annotations and domain shifts. Self-supervised learning (SSL) can address these challenges but remains underexplored in pan-cancer, multi-tracer PET-CT. In this work, we propose MUST-PET (MUltimodal Self-Supervised learning across Tracers), a multimodal, multi-tracer SSL framework for generalizable whole-body PET-CT lesion segmentation. MUST-PET is trained and validated on a diverse, multi-institutional collection of pan-cancer PET-CT scans acquired with FDG and prostate-specific membrane antigen (PSMA)-targeted radiotracers. MUST-PET uses context-aware masked reconstruction, where one modality is partially masked and reconstructed using complementary information from both PET and CT. The pretrained model is subsequently fine-tuned with labeled samples and evaluated for reconstruction quality, lesion segmentation, label efficiency, and generalizability across independent held-out datasets. MUST-PET reduces reconstruction error, improves lesion segmentation over training from scratch, and performs well with limited labeled data and on unseen external datasets, demonstrating the potential of multi-tracer SSL for label-efficient, generalizable whole-body PET-CT. segmentation.

Bashirul Azam Biswas, Amartya Bhattacharya, Biratal Raj Wagle +3

Department of Biomedical Data Science Geisel School of Medicine at Dartmouth Hanover, NH 03755, USA · Radiology Dartmouth Hitchcock Medical Center Lebanon, NH 03766, USA · Radiation Oncology Dartmouth Hitchcock Medical Center Lebanon, NH 03766, USA

Multimodal SSLPET/CT Tumor SegmentationPET/CT ImagingMultimodal LearningCross-Modality Medical Image Segmentation
AskPDF
Aug 18, 2026

Neoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic resonance imaging with clinical variables

Prediction of pathological complete response before neoadjuvant chemotherapy may facilitate more tailored therapeutic planning for breast cancer patients. This work proposes a deep-learning model for pretreatment data only, combining apparent diffusion coefficient maps, dynamic contrast-enhanced magnetic resonance imaging, and clinical variables. The study uses the public ACRIN 6698/I-SPY2 multicenter dataset. The architecture employs EfficientNet-B0 pretrained encoders for image feature extraction and late fusion with clinical information. Multiple clinical variables were evaluated, including age, race, histological type, HR/HER2 subtype, SBR grade, and maximum diameter. Only HR/HER2 subtype improved the average area under the receiver operating characteristic curve (AUC) and was retained in the final model. Using stratified five-fold cross-validation, standalone apparent diffusion coefficient maps achieved a mean AUC of 0.79, whereas dynamic contrast-enhanced magnetic resonance imaging achieved 0.74. Adding HR/HER2 subtype improved performance to 0.83 and 0.81, respectively. The final configuration, using both imaging modalities and HR/HER2 subtype, achieved an AUC of 0.86. These results support pretreatment multimodal learning for response prediction, although external validation is required before clinical use.

Pablo García Marcos, Paula Puerta González, Guillermo Lorenzo +6

Computer Science Department, University of Oviedo, Asturias, Spain · Biomedical Engineering Center (BME), University of Oviedo, Asturias, Spain · Electrical Engineering Department, University of Oviedo, Asturias, Spain +7

Cancer Drug Response PredictionClinical Outcome PredictionOncologyMultimodal Learning
AskPDF
Aug 16, 2026

CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications

Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representation learned in one deployment can fail when viewpoint, traffic, illumination, and propagation geometry change. This paper presents CM-MAE, a self-supervised vision--wireless pretraining framework for cross-scenario representation transfer. The evaluated real-data model uses only RGB frames and the measured 64-beam received-power vector available in DeepSense 6G; it does not use ray-traced paths, calibrated depth, or beam-index labels during pretraining. Its central pretraining term is a soft contrastive alignment loss. Instead of making the synchronized image--wireless pair the only positive pair, this loss builds a target distribution from similarities between measured beam-power profiles, so nonidentical samples with similar directional responses are not forced apart as false negatives. A masked joint decoder provides the complementary local objective by reconstructing hidden visual patches and wireless angular clusters under modality dropout. After pretraining, a differential-rate fine-tuning rule lets a new fusion head adapt quickly while the encoders move slowly. Under a sequence-disjoint DeepSense 6G protocol, adding the soft alignment loss improves a matched linear-probe transfer average from 24.88% to 29.49%. Mild fusion fine-tuning reaches 77.38% Top-1 accuracy on unseen Scenarios 6--8, and optional transductive normalization adaptation reaches 78.69%. Since the fusion setting uses the contemporaneous 64-beam power vector at inference, these results should be read as representation-transfer diagnostics, not as proactive beam-prediction or reduced-sweeping claims.

Yubo Zhang, Yiyao Liu

Cross-Modal Representation LearningSelf-Supervised Pre-TrainingMultimodal LearningTransfer LearningMultimodal Contrastive Learning
AskPDF
Aug 15, 2026

Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs

Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their text-only backbones. While mechanistic evidence from text-only models suggests that non-English inputs are routed through an English-centric latent space, the multimodal implications of this phenomenon remain unexplored. Through rigorous mechanistic analysis, we identify the Ghost Anchor phenomenon: a temporal modality asynchrony where linguistic translation to the English semantic manifold completes in early layers, while visual semanticization remains immature. Consequently, visual signals are physically present yet functionally invisible during the early alignment window. To rectify this, we propose ANCHOR, a training framework employing Proactive Visual Anchoring (PVA) to accelerate early visual semantic emergence, ensuring visual representations proactively guide linguistic translation. Mechanistic interventions confirm that ANCHOR successfully restores the causal influence of visual signals during early translation. Furthermore, extensive experiments on XMMMU, MaXM, and CVQA demonstrate that ANCHOR consistently outperforms standard baselines, achieving robust visual reasoning across both fine-tuned and zero-shot languages.

Yihang Du, Juhao Liang, Zhengzhao Lai +2

The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · National Health Data Institute (Shenzhen)

Multimodal Large Language ModelsVision-Language AlignmentMultimodal LearningMultimodal GroundingMultilingual VLM Evaluation
AskPDF
Aug 15, 2026

PathFinder: Joint Decompositions of Linked Multimodal Datasets

Low-rank matrix decompositions can uncover patterns and structure in data and have a number of different applications across many disciplines. Extensions to "joint" low-rank decompositions have been proposed to link datasets from different modalities. While these methods enable the discovery of common patterns across modalities, they require that all the multimodal data share one or more dimensions. We propose a new analysis method, PathFinder, that enables co-analysis of datasets that do not necessarily all share a dimension. The key insight is that as long as pairs or subgroups of matrices do share some dimension, and that there are one or more paths that link across the data matrices, a global joint decomposition can be sought out. This enables the joint estimation of common patterns across different modalities, species, or scales, where a one-to-one mapping across all data along some dimension is not necessarily available. We show that PathFinder is a general umbrella under which many matrix decomposition methods fall as special cases. It can be used to discover common patterns across disparate datasets and to make predictions for missing data or modalities.

Ying-Qiu Zheng, Alex Fung, Stephen M Smith +2

Oxford Centre for Integrative Neuroimaging University of Oxford Oxford, UK

Low-Rank Matrix DecompositionMatrix FactorizationMultimodal FusionMultimodal Learning
AskPDF
Aug 14, 2026

MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity

Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific modality types, while individual records within the same client may contain different partial modality subsets. Sparse Mixture-of-Experts (MoE) architectures are a promising remedy for modality-adaptive computation, but their use in federated learning is fragile under cross-client modality heterogeneity, where locally learned routing policies can diverge across clients and drive experts toward incompatible specializations. Different clients may assign the same observed modality configuration to different experts, or train similarly indexed experts on different missing-modality configurations, causing standard aggregation to misalign or overwrite the expert specialization that sparse MoEs are intended to learn. To address this challenge, we propose MedMix, a semantic-alignment framework for federated multimodal sparse MoEs that coordinates cross-client routing and expert specialization using modality context. At the client side, MedMix uses modality-context-aware routing to guide expert selection using each token's modality identity, position, and incompleteness context. Across clients, it uses consensus-guided routing alignment to construct server-side consensus anchors for shared modality patterns and align local routing distributions across clients. Complementing these routing mechanisms, client-adaptive expert aggregation leverages client-specific modality-pattern prototypes to match and aggregate functionally similar experts across clients. Experiments on real-world multimodal medical datasets show that MedMix achieves the best average F1 across diverse modality heterogeneity and modality incompleteness settings, with especially clear gains under severe heterogeneity.

Adiba Orzikulova, Dong Min Kim, Jaehong Yoon +1

KAIST · NTU Singapore

Multimodal Federated LearningFederated LearningSparse Mixture-of-ExpertsHeterogeneous Federated LearningMultimodal LearningFederated Learning Aggregation
AskPDF
Aug 10, 2026

Hyperbolic Multimodal Continual Learning

Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplored. This work provides a geometric perspective on this problem and establishes a theoretical foundation for representation preservation in hyperbolic space, showing that preventing forgetting requires cross-modal invariance under a shared hyperbolic isometry. We further show that forgetting in hyperbolic continual learning involves both semantic relation drift and hierarchy-related distortion, motivating preservation of both cross-modal relational structure and hierarchical geometry. Guided by these insights, a principled continual learning framework is derived that preserves essential geometric structure while allowing effective adaptation to new tasks. Experiments on continual multimodal benchmarks corroborate the effectiveness of the proposed approach.

Jiahong Liu, Ming Shen, Xiaohao Liu +4

Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China · School of Computing, National University of Singapore, Singapore · Department of Computer Science, Yale University, New Haven, CT, United States +1

Cross-Modal Representation LearningInvariant Representation LearningHyperbolic Representation LearningMultimodal LearningCatastrophic Forgetting
AskPDF
Aug 10, 2026

Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation

Multimodal embedding models are deployed at scale: retrieval indices, benchmark results, and behavioral audits all depend on the base model's exact outputs. Extending such a model to a new modality with existing parameter-efficient methods silently changes those outputs; LoRA-style adaptation rewrites the text path whether or not the weights are merged, invalidating every stored embedding. We propose modality-gated deep adapters: bottleneck adapters attached to every decoder layer of a frozen multimodal embedding LLM, grouped into per-modality packs that execute only while their own modality is being encoded. The result is a modality added with zero change to existing outputs: inputs no pack claims traverse the base model's own computation graph, bit-for-bit unchanged, and co-loaded packs compose with an exact-zero isolation matrix. Both properties are stated as propositions, hold after arbitrary training rather than only at initialization, require no task labels or routing metadata at inference, and are verified by exact-equality tests on the released checkpoints. On one frozen 2B base, the audio pack (injected as connector tokens) improves audio-to-text R@10 by +3.4 to +5.4 points over an identically trained control, positive at every seed and reproduced at eleven times the data; the thermal pack, reusing the base's own frozen vision path, clears its pre-registered acceptance gate roughly sevenfold at every seed and lifts thermal-to-text R@10 from 0.224 to 0.785. An encoder swap locates the missing capacity: an external audio encoder that outranks Whisper-family encoders in CLAP-style comparisons loses by 16 R@10 points inside the frozen LLM, so the capacity belongs in the layers, exactly where the gated adapters place it. We release the audio model, the thermal pack, and the training, evaluation and invariance suites: models at huggingface.co/EximiusLabs, code on GitHub.

Abdul Basit Tonmoy, Kazi Fardinul Hoque, Md. Shahrier Islam Arham +1

Eximius Labs · Wabash College · Skop Intelligence Co.

Multimodal EmbeddingAdapter TuningMultimodal LearningParameter-Efficient Fine-TuningCross-Modal Retrieval
AskPDF
Aug 7, 2026

Conformal Calibration for Multi-Modal Regression with Missing Modalities

Prediction intervals for multi-modal regression with tabular variables, text, images, or other input sources are difficult to calibrate when those sources disagree or one is missing. A single global quantile averages these regimes together instead of calibrating to the modality pattern observed at test time. We address this through a modality-aware conformal calibration layer. The layer trains or reuses one predictor per modality, computes a disagreement score from their predictions, and uses that score in split conformal calibration under a strict split protocol. We use the score in two complementary ways. First, a continuous disagreement-scaled method reallocates interval width across examples while preserving the usual marginal split-conformal guarantee. Second, a Mondrian (stratified) method calibrates within groups defined by disagreement or modality availability fixed before calibration, giving group guarantees under joint exchangeability of the calibration and test examples. Across four multi-modal datasets, the disagreement-scaled layer matches or improves the marginal conformal baseline in 59 of 60 paired runs for interval continuous ranked probability score (CRPS) and in 52 of 60 for interval width, while keeping empirical coverage near the 95% target. In stress tests with missing modalities, mask-matched recalibration recovers up to 19.5 percentage points of coverage in the hardest fixed-mask regime. The result is a simple, model-agnostic reliability layer for multi-modal regression systems. A project page is available at https://unco3892.github.io/modality-aware-conformal.

Ilia Azizi

Department of Operations, HEC Lausanne, University of Lausanne, Switzerland · BegooAI, Switzerland

Group-Conditional Conformal PredictionMultimodal RegressionModel CalibrationMultimodal LearningRegression Prediction Intervals
AskPDF
Aug 7, 2026

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-kk page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration. DocMemo maintains a tri-level retrieval state consisting of Document Schema Memory, Page Belief Memory, and Question Episodic Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific reasoning trajectories. During reasoning, DocMemo continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.

Hanshu Yao, Janfeng Zhong, Niu Lian +1

1Harbin Institute of Technology, Shenzhen · 2Tsinghua Shenzhen International Graduate School, Tsinghua University

Multimodal MemoryDocument QAVisual Document RetrievalEvidence RetrievalMultimodal Learning
AskPDF
Aug 7, 2026

Walkable to Whom? Capturing Subjective Variability in Walkability Perception Using Multimodal Deep Learning

Visual perception of walkability varies substantially across individuals, reflecting differences in personal characteristics, experiences, and preferences. Existing studies, however, often reduce these diverse judgements to aggregated scores, implicitly assuming uniform perception, and commonly rely on vehicle-mounted street-view imagery that does not reflect the pedestrian's visual experience. This paper introduces a dataset of 29,870 walkability ratings from 1,196 respondents, linking sidewalk-view imagery across urban, suburban, and regional Australian environments with individual rater attributes, and proposes the first user-conditioned multimodal deep learning framework for walkability perception, fusing visual features with respondent-level representations. A viewpoint-comparison study shows that sidewalk-view images receive significantly higher walkability ratings than matched street-view images, indicating that imagery source is a substantive design decision in perception surveys. The user-conditioned model improves rank agreement with observed ratings by 65% over an image-only baseline (quadratic weighted kappa 0.47 vs. 0.29), demonstrating that who is evaluating an environment carries predictive indication beyond image content alone. These findings support moving from aggregated, observer-independent walkability scores toward models that represent diverse users, enabling more inclusive assessment of pedestrian environments.

Moloud Damandeh, Meead Saberi

School of Civil and Environmental Engineering, University of New South Wales (UNSW), Sydney, NSW, Australia, and the Research Centre for Integrated Transport Innovation (rCITI)

User ModelingUrban PlanningMultimodal Learning
AskPDF
Aug 6, 2026

F2^2Agent: Financial Fusion of Agentic Intelligence for Multimodal Trading

With increasingly diverse and heterogeneous information sources, effectively leveraging multimodal data is becoming pivotal for high-quality financial trading. Although recent advancements in Large Language Model (LLM)-based agents have enabled the ingestion of multimodal inputs, existing methods fail to capture nuanced cross-modal dependencies and remain vulnerable to market noise, due to limited multimodal modeling, ineffective fusion mechanisms, and inadequate robustness. To address these challenges, we propose F2^2Agent, a novel multimodal agentic paradigm driven by the Financial Fusion of Agentic Intelligence. F2^2Agent first deploys a hierarchy of specialized agents to comprehensively extract modality-specific signals. It further introduces a modality-aware adaptive fusion mechanism coupled with noise-robust consistency regularization to dynamically capture fine-grained inter-modality dependencies and generate noise-resilient trading signals. Extensive experiments on six stocks and cryptocurrency assets demonstrate that F2^2Agent consistently outperforms 16 competitive baselines across multiple trading metrics, with over 20% relative improvement in annualized return on average. Notably, F2^2Agent delivers returns of 120.48% on GOOG and 148.41% on TSLA, demonstrating its efficacy and robustness in varying market dynamics.

Changshuo Liu, Yanzheng Jin, Shangfeng Cai +3

National University of Singapore · Huazhong University of Science and Technology · Zhejiang University

Multimodal AgentsMultimodal FusionMultimodal LearningAlgorithmic Trading
AskPDF
Aug 5, 2026

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw privileged information from diverse input sources to guide self-distillation. Yet these designs overlook Modality Imbalance, a challenge inherent to MLLM reasoning. When textual information dominates generation, the model cannot fully integrate its multimodal input. Consequently, carefully designed privileged information remains underused, limiting the effectiveness of OPSD. To examine this limitation, we construct a Positive Teacher with the Zoom-In Image and a Negative Teacher with the Mask Image, which exhibit different degrees of Modality Imbalance. Changes in their reasoning correctness and token logits reveal that Modality Balance can itself serve as privileged information. Motivated by this finding, we introduce OPD-V, a visual OPSD paradigm that instantiates such information through the Positive Teacher and Negative Teacher. Positive Modality-Balance Logits Margins define a Modality-Balance Trust Region that selects the on-policy tokens used for self-distillation. Experiments across 6 benchmarks, 4 MLLM backbones, and 5 post-training methods show that OPD-V consistently improves reasoning performance while reducing training cost.

Aniri, Jinhe Bi, Peng Liao +5

2Ludwig Maximilian University of Munich · 3Munich Center for Machine Learning · 1National University of Singapore +1

Modality ImbalanceOn-Policy Self-DistillationVLM DistillationMultimodal Large Language ModelsVLM ReasoningMultimodal Learning
AskPDF
Aug 5, 2026

iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data

Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalization problems. To tackle this challenge, we introduce Graph-Enhanced Descriptor Sequencing (GEDS), a structured feature sequencing algorithm grounded in principles from the Column Permutation Problem (CPP). GEDS refines statistical descriptors of the features through similarity graph-based computations, systematically determining an effective feature sequencing. We incorporate GEDS within an order-aware efficient transformer framework, utilizing order-aware memory tokens that explicitly adhere to the derived feature sequencing via a dedicated loss function. Experimental results across multimodal benchmarks demonstrate that iStructTab effectively minimizes feature dispersion, improving predictive performance and robustness, and highlighting the significance of structured feature sequencing in multimodal learning.

Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali +2

Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506, USA · Scientific Computing and Imaging Institute & Department of Biomedical Informatics, The University of Utah, Salt Lake City, UT 84112, USA

Sequence ModelingMultimodal Learning
AskPDF
Aug 3, 2026

DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing

Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance. A central challenge is determining the fusion granularity across modalities: over-integration may amplify noise while under-integration fails to exploit cross-modal dependence. Existing approaches rely on pre-specified fusion architectures, from early to late fusion, that may not adapt to the underlying dependence structure among modalities. We propose DAIF, a data adaptive intermediate fusion framework that combines random matrix theory and non-parametric dependence measures to learn fusion structure directly from data. We operate under a Bayesian multimodal factor model where the prior on the latent factors determines the cross-modal dependence. Our method clusters modalities based on estimated intermodal dependence, then performs clusterwise empirical Bayes estimation of the priors. These estimated priors are used to construct denoisers within an approximate message passing (AMP) framework, yielding denoised low-dimensional features that borrow strength across related modalities while preserving modality-specific signal. The resulting embeddings are used for downstream supervised prediction. We evaluate the framework through simulations under varying dependence structures and signal regimes, comparing against several benchmark methods, and demonstrate its practical utility on two multimodal datasets, namely a trimodal TEA-seq dataset (Swanson et al., 2021) and TCGA-BRCA dataset (Goldman et al., 2020). In the first example, we predict the expression level of a T-cell differentiation marker protein and in the second case we analyze patient survival prediction based on multimodal information. Our method competes with or outperforms the state-of-the-art techniques in both prediction problems, demonstrating its versatility across diverse supervised learning tasks.

Sagnik Nandy, Samriddha Lahiry, Pragya Sur +1

Ohio State University · National University of Singapore · Harvard University

Latent Variable ModelsApproximate Message PassingMultimodal FusionMultimodal Learning
AskPDF
Aug 3, 2026

SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks

Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention with channel-wise spike co-activation and self-compensation, and (iii)SMoE, a spiking mixture-of-experts module for modality-aware fusion. Across visual and multimodal benchmarks, SMM Transformer achieves competitive accuracy compared to ANN baselines. Under a standard MAC/AC arithmetic model, SMSA reduces the estimated operator-level compute energy of the attention module by up to 97%, while whole-model profiling shows more moderate but consistent efficiency gains.

Xiubo Liang, Jinxing Han, Yuke Li +3

School of Software Technology, Zhejiang University, Ningbo, China · NetEase Yidun AI Lab, Hangzhou, China

Spiking TransformersSpiking Neural NetworksMultimodal FusionMultimodal Learning
AskPDF
Jul 31, 2026

CALM-AH: An ABAW11-Calibrated Multimodal Ensemble with Reliability-Gated Multi-Expert Consensus for Video-Level Ambivalence and Hesitancy Recognition

Ambivalence and hesitancy (A/H) are subtle behavioural states that may be expressed through language, voice, facial activity, and other non-verbal cues. The ABAW11 A/H Video Recognition Challenge asks systems to assign a binary A/H label to each naturalistic interview video. Performance is measured using Macro-F1 so that recognition of both A/H and No-A/H samples receives equal importance. We present CALM-AH, a multimodal ensemble that combines textual, acoustic, visual, and derived behavioural-statistical features. We construct 15 non-empty combinations of these feature branches. For each combination, we select the best of three classifier families using validation binary cross-entropy and optimise its decision threshold for validation Macro-F1. The resulting binary decisions are combined using fixed hard-voting weights transferred from BROTHER. We further introduce Reliability-Gated Multi-Expert Consensus(RG-MEC), an anchor-preserving decision-level ensemble that combines an initial prediction with three complementary correction experts: CALM-AH, AffectGPT, and a GPT-based semantic verifier. The initial system provides the default prediction. Its label is overridden only when all three correction experts unanimously support the same alternative class; otherwise, the anchor prediction is retained. This unanimity-gated design limits the influence of isolated expert errors while permitting bidirectional correction when task-specific, multimodal-affective, and semantic-pragmatic evidence are fully consistent. On the participant-disjoint ABAW11 dataset, CALM-AH achieves a Macro-F1 of 0.7525, and the complete RG-MEC system achieves 0.7771.

Wenzhuo Sun, Mingjian Liang, Richard Attfield +3

Monash University, Melbourne, Australia · Monash Suzhou Research Institute, Suzhou, China

Ensemble LearningMultimodal Emotion RecognitionAmbivalence and Hesitancy RecognitionMultimodal Learning
AskPDF
Jul 29, 2026

What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations

A central premise of latent world models is that predicting the future forces a representation to internalize the physics of its environment. Which physical quantities does a trained latent actually contain, and what decides this? We answer with controlled interventions in POKEWORLD, an interactive environment whose visually identical objects hide mass, drag, and contact stiffness. A certificate-gated protocol first certifies each parameter as recoverable from raw observations, then measures whether it enters the latent, so a null result can be attributed to the objective rather than to the environment. The resulting identifiability map has two organizing mechanisms and one frontier. Inputs limit what can be known, while prediction targets decide what is retained. Stiffness enters the latent only when touch is forecast (R2=0.50R^2=0.50, compared with −0.02-0.02 when the same signal is merely fused into the input), and under single-step prediction a vision-only latent discards even perfectly visible object state. Drag marks the frontier. It carries a recoverability certificate of 0.89 yet plateaus near 0.13 under every deterministic prediction objective we test, while a supervised head on the same trunk reaches 0.45. Parameters whose readout is slow and ratio-type under the sensed coordinates fall outside what these objectives acquire. On RH20T, an input-target factorial across scaling curves reproduces both mechanisms across two robots and 4,258 episodes. Every arm missing information or prediction pressure stays flat over a fivefold data range, and only the full multimodal objective forecasts force beyond a persistence baseline, with held-out gains that grow with scale. Objective structure determines which physical parameters a latent acquires, and additional data improves only the parameters it already acquires.

Kaizhen Tan, Xin Xu, Siru Tao +4

New York University, New York, NY, USA · Carnegie Mellon University, Pittsburgh, PA, USA · Columbia University, New York, NY, USA

Parameter IdentifiabilityPredictive Representation LearningLatent World ModelsMultimodal Learning
AskPDF
Jul 29, 2026

Regularizing modality contribution drift in multimodal continual learning

Multimodal continual learning (MMCL) aims to learn emerging knowledge from multimodal data while preserving knowledge. To mitigate forgetting, current MMCL methods usually focus on cross-modal representation alignment or semantic similarity, but they overlook whether the relative contributions of individual modalities and their interactions remain stable across incremental tasks. We term this decision-level shift Modality Contribution Drift (MCD) and quantify it with the MCD score, which combines contribution-strength and relative-reliance changes under controlled interventions on modality subsets. Theoretical and empirical analyses further explain why current MMCL methods cannot reliably mitigate this drift. To this end, we propose Continual Modality Contribution Drift Regularization (CMCDR), which preserves the modality contribution structure of previously learned tasks. Since MMCL settings differ in whether old exemplars are available, CMCDR includes both replay-based and replay-free versions. The replay-based version uses modality-subset interventions as diagnostic probes on stored old samples, compares their contribution profiles between the current model and a frozen previous model, and constrains changes in old-sample modality-specific and interaction contributions. The replay-free version uses current-task samples as probes and distills the frozen model's old-task contribution responses, thereby regularizing the observed contribution profile without exemplars. Experiments on multimodal class-incremental learning and continual visual question answering validate the generality and effectiveness of CMCDR.

Zhen Zhang, Jielei Chu, Bin Liu +1

School of Computing and Artificial Intelligence, Southwest Jiaotong University

Multimodal Learning
AskPDF
Jul 28, 2026

From Cellular Responses to Pharmacological Domains: Multimodal Zero-Shot Drug Representation Learning

Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology. However, direct fusion and instance-level contrastive alignment may mix mechanism-related signals with modality-specific noise and incorrectly separate structurally dissimilar but biologically related compounds. This limitation can obscure transferable mechanism patterns required for predicting the properties of unseen compounds. We introduce PMRD, a pharmacological response domain-guided framework for multimodal zero-shot drug property prediction. PMRD separates mechanism-consistent factors from modality-specific information and constructs a consensus response domain across three modalities. Mechanism candidate augmentation identifies locally stable factors, while retrieval-geometry attribution dynamically reweights the alignment and augmentation objectives according to whether their updates preserve inter-drug discriminability.This feedback suppresses training signals that conflict with mechanism-discriminative retrieval. PMRD further combines complementary representations through reliability-aware multiview retrieval. Experiments on public datasets show improved zero-shot property prediction and more biologically coherent drug neighborhoods. Hard-negative analysis further indicates fewer conflicts between structurally dissimilar but response-related compounds. These results support PMRD as an effective framework for mechanism-aware multimodal drug representation learning.\footnote{The code will be released upon publication.}

Jintao Huang, Lu Leng, Ziyuan Yang

Nanchang Hangkong University, Nanchang, Jiangxi, China · Sichuan University, Chengdu, Sichuan, China

Cross-Modal RetrievalMolecular Property PredictionMultimodal LearningMolecular Representation Learning
AskPDF
Jul 27, 2026

Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification

Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational constraints, such as sensor failures or privacy restrictions, lead to inconsistent modality availability between training and inference times. To handle missing modalities, prior studies have mainly covered bimodal data setups and focused on designing robust fusion processes. Instead, we adopt a multi-modal co-learning framework that prioritizes inter-modal collaboration rather than multi-modal fusion. Specifically, we consider that any subset of modalities may be absent, without assuming predefined missing-modality patterns, an inference scenario we refer to as missing arbitrary modalities. To address this challenge, we introduce two alternative approaches that leverage information at both feature- and decision-level. Experiments on two multi-modal classification benchmarks demonstrate significant robustness gains in various missing modality conditions. The first method shows more robust behavior under minimal missing conditions, where a single modality is absent, whereas the second performs better under extreme missing conditions, where all-but-one modalities are missing. Our code is available at https://github.com/fmenat/Co4Miss.

Francisco Mena, Dino Ienco, Roberto Interdonato +2

GFZ Helmholtz Center for Geosciences, Potsdam, Germany · INRAE, UMR TETIS, University of Montpellier, Montpellier, France · INRIA, EVERGREEN, University of Montpellier, Montpellier, France +1

Missing-Modality LearningMultimodal RobustnessMultimodal ClassificationMultimodal Learning
AskPDF
Jul 24, 2026

Twins: Learn to Predict Unified Representations with Focal Loss

Unified multimodal models seek a shared visual token space that supports both multimodal understanding and image generation. Discrete methods unify the interface via a shared codebook, whereas continuous pipelines often rely on two disparate representations -- semantic features (e.g., ViT) for understanding and low-level latents (e.g., VAE) for synthesis -- resulting in mismatched latent spaces. We propose Twins, a unified continuous token space formed by channel-wise concatenating ViT and VAE features on the same token grid, so the sequence length is unchanged and attention cost does not increase. However, jointly modeling Twins in a Diffusion Transformer exposes a severe optimization imbalance: the model fits the ViT component well but struggles to match the VAE latent distribution. We trace this imbalance to three sources of heterogeneity: frequency bias, intrinsic dimensionality, and condition-aligned vs condition-independent uncertainty. To address it, we adapt a focal regression objective for flow matching that upweights large-error VAE dimensions, better balancing optimization across the ViT and VAE components. On ImageNet, this yields up to 10.57 gFID gain over naive MSE loss without classifier-free guidance. Twins also performs competitively on multimodal understanding benchmarks and improves reconstruction fidelity, narrowing the gap between understanding- and generation-oriented representations.

Kaixiong Gong, Xin Cai, Bin Lin +9

The Chinese University of Hong Kong · Tencent, Hunyuan · City University of Hong Kong +2

Focal LossDiffusion TransformerUnified Multimodal ModelsMultimodal GenerationMultimodal LearningMultimodal Transformer
AskPDF
Jul 22, 2026

Generative and multimodal AI for materials prediction and design: Progress, challenges, and perspectives

Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with particular promise for novel materials discovery. However, novelty in materials discovery encompasses chemical plausibility, structural distinctiveness, property relevance and experimental realisability, making AI-driven novelty claims difficult to substantiate. We introduce a materials property hierarchy, from intrinsic, composition-determined properties to extrinsic, processing-dependent performance, to clarify deployment constraints and distinguish structural, physical and deployment novelty. This framework motivates an evidence-based view of multimodal materials data spanning chemical composition, microstructure, processing, and testing and characterisation, showing that current evidence remains concentrated in composition and idealised structure while heterogeneous, under-represented and weakly integrated modalities limit support for physical and deployment novelty. It also highlights the limitations of benchmarks based mainly on computational labels and proxy novelty criteria. Community-wide standards for data collection, modality alignment and evidence synthesis are needed to support multimodal data construction, process-aware multimodal modelling, feasibility-first generative modelling and deployment-aware benchmarking, so that generative and multimodal AI can design experimentally realisable materials with defensible scientific and practical novelty.

Xianyuan Liu, Charles Anjah, Benjamin E. Jolly +9

School of Computer Science, University of Sheffield, Sheffield, UK · Centre for Machine Intelligence, University of Sheffield, Sheffield, UK · School of Chemical, Materials and Biological Engineering, University of Sheffield, Sheffield, UK +3

Materials Property PredictionMaterials ScienceMultimodal GenerationMultimodal Learning
AskPDF
Jul 22, 2026

Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction

Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches rely solely on audio and text. This omits crucial visual cues, such as facial expressions and gestures, as well as broader conversational contexts, which are necessary for accurate prediction. In this paper, we introduce Context-Aware Multimodal Alignment for Backchannel Prediction (CAMA-BC), a novel framework that leverages visual information through Multi-Layer Multimodal Alignment (MMA). Our alignment process comprises two stages. First, Context Alignment (MMA-CA) utilizes unlabeled dialogues with videos to capture conversational contexts. Next, Backchannel Alignment (MMA-BA) fine-tunes the representations specifically for backchannel prediction. Experimental results show that CAMA-BC significantly outperforms both existing methods and simple multimodal baselines, with particular effectiveness in recognizing complex backchannels such as empathy.

Min-Jae Kim, Jun-Yeong Moon, Mujeen Sung +1

1Korea University, Seoul, Republic of Korea · 2Kyung Hee University, Yongin, Republic of Korea

Cross-Modal AlignmentMultimodal Learning
AskPDF
Jul 22, 2026

A Unified Tokenization Framework for Pain Recognition using Heterogeneous 3D Modalities

Pain is a complex and pervasive phenomenon affecting a large percentage of the population, and accurate assessment is essential for effective clinical management and intervention. Computational pain recognition systems enable continuous monitoring, support clinical decision-making, and help mitigate pain-related distress and functional decline. This study introduces a unified tokenization framework for heterogeneous 3D modalities in pain recognition that provides a single processing pipeline across behavioral and brain-activity 3D data, without requiring separate architectures for each modality or handcrafted inductive biases. The framework preserves spatial, temporal, and time--frequency structure while mapping diverse inputs into a shared token space. Extensive experiments show that the proposed approach effectively processes facial videos and fNIRS data in both raw-signal and spectrogram-based representations. On the AI4Pain benchmark dataset, the proposed framework achieves state-of-the-art performance while maintaining high computational efficiency and enabling real-time assessment on both GPU and CPU hardware.

Stefanos Gkikas, Christian Arzate Cruz, Valentina Becchetti +3

Honda Research Institute Japan Wako City, Japan · Sapienza University of Rome Rome, Italy · University of Canberra Canberra, Australia

Multimodal Learning
AskPDF
Jul 20, 2026

Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning

Contrastive learning is increasingly moving toward settings with three or more modalities instead of image-text pairs. Yet, extending models from pairwise to higher-order multimodal alignment can introduce optimization and representation challenges. We identify encoder Jacobian conditioning as a key factor in trimodal contrastive learning: poorly conditioned encoders exhibit collapsing or amplified singular-value spectra, leading to exploding Jacobian condition numbers and degraded multimodal alignment. We introduce geometry-preserving encoders (GPEs) by directly conditioning the Jacobian through regularization and demonstrating that simple modifications like LeakyReLU activations and residual paths recover these geometric benefits. Across a synthetic benchmark and four real-world datasets including missing modalities, improving Jacobian conditioning boosts retrieval and linear probe performance across multiple contrastive objectives, whereas expressive objectives yield little benefit in linear probes. More broadly, our results show that multimodal contrastive learning depends not only on objective expressivity, but also on the geometric and optimization properties of the underlying encoders.

Tillmann Rheude, Roland Eils, Benjamin Wild

Berlin Institute of Health, Charité - Universitätsmedizin Berlin · Department of Mathematics and Computer Science, Freie Universität Berlin · Intelligent Medicine Institute, Fudan University

Geometric Representation LearningMultimodal Contrastive LearningMultimodal Learning
AskPDF
Jul 18, 2026

MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning

Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, making end-to-end multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and control. We introduce MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models. MultiLoReFT extends low-rank adaptation to the multimodal setting and learns interpretable projection subspaces that decouple shared and modality-specific information. Across simulated and real-world benchmarks, it produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across modalities.

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler

Massachusetts Institute of Technology, Cambridge, MA, USA · Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, MA, USA · Vector Institute, Toronto, Canada +1

Cross-Modal Representation LearningMultimodal Disentangled Representation LearningRepresentation DisentanglementMultimodal Model InterpretabilityMultimodal LearningParameter-Efficient Fine-Tuning
AskPDF