Paper presents a method to align unpaired samples across different modalities.
problem Challenges in collecting paired samples for multimodal representation learning.
method Uses propensity score alignment based on Rubin's framework to estimate a common space for unpaired samples.
result Optimal transport matching significantly improves alignment in real-world data.
DTA aligns multimodal data with prior correspondence knowledge.
problem Challenges in aligning data from different domains.
method Semi-supervised manifold alignment method exploiting prior correspondence knowledge.
result DTA outperforms other methods in aligning multimodal data.
Unified model integrates text and time series for financial forecasting.
problem Challenges in integrating complementary modalities for improved forecasting.
method Modality-specific experts and cross-modal alignment framework.
result State-of-the-art performance on financial forecasting task.
Improved text-to-image and multimodal understanding through adaptive generation order optimization.
problem Determining optimal generation sequences in text-to-image synthesis and multimodal understanding.
method Introduced a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order.
result Learning the control block substantially improves text-to-image alignment and multimodal understanding in DLMs.
HCL learns shared and modality-specific latent representations for multimodal data.
problem Binary shared-private decomposition inadequately represents shared information across subsets of modalities.
method Hierarchical Contrastive Learning framework combining latent-variable formulation, structural sparsity, and contrastive objective.
result HCL accurately recovers hierarchical structure and improves predictive performance on multimodal data.
Framework improves clinical timeline reconstruction from text and tables.
problem Temporal precision and event timing in clinical narratives and EHRs.
method Retrieval-augmented multimodal alignment framework.
result Consistently improves absolute timestamp accuracy and temporal concordance.
Geometric method captures rare topics and temporal alignment in co-author networks.
problem Missing rare topics and smooth temporal alignment in topic modeling.
method Integrates multimodal text and co-author network data using Hellinger distances and Ward's linkage.
result Effective identification of rare topics and visualization of topic drift over time.
We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical registration approaches include feature design and slow optimization by gradient descent. By analyzing these methods, we note the significa…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…
Proposes a copula-driven framework for multimodal learning.
problem Aligning and fusing representations from multiple modalities with complex interactions.
method Copula model for joint distribution of modalities, Gaussian mixture for marginal distributions.
result Superior performance on public MIMIC datasets.
In many machine learning applications, it is necessary to meaningfully aggregate, through alignment, different but related datasets. Optimal transport (OT)-based approaches pose alignment as a divergence minimization problem: the aim is to transform a source dataset to match a target dataset using the Wasserstein dista…
GGMPs improve non-Gaussian conditional density estimation.
problem Multimodality, heteroscedasticity, and strong non-Gaussianity in conditional density estimation.
method GGMP combines local Gaussian mixture fitting, cross-input component alignment, and per-component heteroscedastic GP training.
result GGMPs improve distributional approximation on synthetic and real-world datasets.
A new mathematical framework for multimodal learning.
problem Linking different data modalities for better understanding.
method Interpreting contrastive learning as optimizing encoders for conditional probability distributions.
result Novel probabilistic loss functions and metrics for alignment in latent space.
We introduce a kernel method for manifold alignment (KEMA) and domain adaptation that can match an arbitrary number of data sources without needing corresponding pairs, just few labeled examples in all domains. KEMA has interesting properties: 1) it generalizes other manifold alignment methods, 2) it can align manifold…
This paper improves cross-domain learning using random forests for manifold alignment.
problem Improving cross-domain learning and feature integration.
method Semi-supervised manifold alignment using random forest proximities.
result Random forest proximities enhance downstream classification accuracy.
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propo…
PLS-SVD struggles with missing data in multimodal datasets, showing a phase transition in performance.
problem Missing data in PLS-SVD for multimodal datasets.
method Replica-symmetric analysis of spiked rectangular random matrices with missing entries.
result PLS-SVD performance transitions from uninformative to informative singular vectors at a critical signal-to-noise threshold.
New method clusters multimodal data with consistency.
problem Multimodal clustering with unaligned data.
method Conjugate mixture models and EM algorithm.
result Consistent multimodal clustering achieved.
MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.
problem Challenges in multimodal learning, especially in healthcare and daily living.
method Dynamic intra- and cross-modal interactions, symbolic tokenization, adaptive attention budgeting, sparse cross-modal attention, MoE mechanism.
result Average relative improvements of 4% and 8% over existing multimodal and multivariate approaches, respectively, under complete observations.
Study enhances cryptocurrency sentiment analysis using TikTok and Twitter data.
problem Lack of comprehensive sentiment analysis in cryptocurrency markets.
method Multimodal analysis of TikTok and Twitter data using large language models.
result TikTok's video sentiment influences speculative assets and short-term trends.
Deep RL model uses multimodal data for better stock portfolio optimization.
problem Optimizing trading strategies for SP100 stocks using complex data sources.
method Multimodal deep reinforcement learning with state tensors, CNNs, and RNNs.
result Agent outperforms standard benchmarks in portfolio performance.
Study creates a multimodal learning framework for CVD risk prediction.
problem Predicting cardiovascular disease risk in diverse populations.
method Combines cross modal transformers, graph neural networks, and causal representation learning.
result Model predicts personalized CVD risk with causal invariance across subpopulations.
Graph matching is a challenging problem with very important applications in a wide range of fields, from image and video analysis to biological and biomedical problems. We propose a robust graph matching algorithm inspired in sparsity-related techniques. We cast the problem, resembling group or collaborative sparsity f…
Two semi-supervised manifold alignment methods improve cross-domain classification.
problem Aligning data from multiple sources for better analysis.
method SPUD and MASH methods using graph integration and diffusion.
result SPUD and MASH methods outperform existing methods in cross-domain classification.
TRACE improves conformal prediction for multi-dimensional outputs.
problem Challenges in constructing valid and informative conformal prediction regions for multi-dimensional outputs.
method TRACE uses transport alignment in diffusion and flow matching models to define nonconformity scores.
result TRACE yields valid and adaptive conformal prediction regions for multimodal and non-convex distributions.
Unified framework for generating meteorological time series from text.
problem Lack of large-scale, physically grounded multimodal datasets and architectures ignoring spectral-temporal structure.
method Introduce MeteoCap-3B dataset and MTransformer model.
result State-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability.
New method identifies shared components from unpaired multimodal mixtures.
problem Identify shared components from unpaired multimodal mixtures.
method Distribution divergence minimization-based loss with sufficient conditions for identifiability.
result Sufficient conditions for shared component identifiability from unaligned multimodal mixtures.
GROOVE learns representations for weakly paired multimodal data.
problem Learning representations for high-content perturbation data with weakly paired samples.
method GroupCLIP contrastive loss integrated with an autoencoder framework.
result GROOVE performs on par with or outperforms existing approaches for cross-modal tasks.
Paper reviews the evolution of alpha from human insight to AI-powered systems.
problem Exceeding market benchmarks in finance.
method Five-stage taxonomy integrating representation learning, multimodal data fusion, and LLM agents.
result Unified framework for evaluating and developing next-gen alpha systems.
OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.
problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.
Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities. The central challenge in multimodal learning involves learning representations that can process and relate information from multiple modalities. In this paper, we propose two methods for unsupervised learning of j…
FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.
problem Improving adversarial transferability for closed-source MLLMs, especially with high accuracy.
method Unified frequency-domain regularization approach: high-pass DCT objective for feature alignment and Frequency-domain Gradient Regularization (FGR) for gradient optimization.
result FRA-Attack achieves superior cross-model transferability, especially on GPT-5.4, Claude-Opus-4.6, and Gemini-3-flash.
Survey of multimodal deep generative models for diverse data types.
problem Inference of shared representations and cross-modal generation from heterogeneous multimodal data.
method Variational autoencoders and other deep generative models.
result A comprehensive survey of multimodal deep generative models.
Multimodal fusion is considered a key step in multimodal tasks such as sentiment analysis, emotion detection, question answering, and others. Most of the recent work on multimodal fusion does not guarantee the fidelity of the multimodal representation with respect to the unimodal representations. In this paper, we prop…
Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact multimodal representation. Previous research in this field has exp…
Develops a contrastive framework for data-efficient multimodal learning.
problem Expensive training of multimodal generative models requiring related multimodal data.
method Contrastive framework for multimodal learning, distinguishing related from unrelated data.
result Data-efficient multimodal learning on challenging datasets for various VAE models.
Learning multimodal representations is a fundamentally complex research problem due to the presence of multiple heterogeneous sources of information. Although the presence of multiple modalities provides additional valuable information, there are two key challenges to address when learning from multimodal data: 1) mode…
Multimodalities provide promising performance than unimodality in most tasks. However, learning the semantic of the representations from multimodalities efficiently is extremely challenging. To tackle this, we propose the Transformer based Cross-modal Translator (TCT) to learn unimodal sequence representations by trans…
Humor is a unique and creative communicative behavior displayed during social interactions. It is produced in a multimodal manner, through the usage of words (text), gestures (vision) and prosodic cues (acoustic). Understanding humor from these three modalities falls within boundaries of multimodal language; a recent r…
Paper proposes multimodal contrastive learning for EHR data.
problem Separate treatment of structured and unstructured EHR data.
method Proposes a multimodal feature embedding generative model and a multimodal contrastive loss.
result Multimodal learning yields better feature representation than single-modality learning.
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised mult…
Study quantifies interactions between unlabeled multimodal data.
problem Understanding how modalities combine in semi-supervised settings.
method Information-theoretic definitions and bounds derivation.
result Validated lower and upper bounds accurately track true interactions.
Study analyzes bias interactions in multimodal models using simulation-based methods.
problem Analyzing dynamic bias interactions in multimodal models to ensure fairness and equity.
method Simulation-based heuristic approach to compute bias scores for text-only, image-only, and multimodal embeddings.
result Multimodal bias interactions can be amplification, mitigation, or neutral, with text bias often dominant.
We view molecular optimization as a graph-to-graph translation problem. The goal is to learn to map from one molecular graph to another with better properties based on an available corpus of paired molecules. Since molecules can be optimized in different ways, there are multiple viable translations for each input graph…
The complex world around us is inherently multimodal and sequential (continuous). Information is scattered across different modalities and requires multiple continuous sensors to be captured. As machine learning leaps towards better generalization to real world, multimodal sequential learning becomes a fundamental rese…
The study characterizes diffusion model generalization using data-dependent ridge manifolds.
problem Understanding where diffusion model-generated samples lie when not memorizing the training set.
method Introduced a time-dependent family of log-density ridge manifolds to characterize reverse-time inference.
result Generated samples evolve by a reach-align-slide mechanism, controlled by normal and tangential components of training error.
Class-conditional generative models are crucial tools for data generation from user-specified class labels. Existing approaches for class-conditional generative models require nontrivial modifications of backbone generative architectures to model conditional information fed into the model. This paper introduces a plug-…