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.
Paper proposes MAG to fine-tune BERT and XLNet for multimodal sentiment analysis.
problem Fine-tuning pre-trained models for multimodal language applications is challenging.
method Integrates vision and acoustic modalities into BERT and XLNet through Multimodal Adaptation Gate (MAG).
result Significant improvement in multimodal sentiment analysis performance over previous methods.
This research improves multimodal systems by adding a second objective and regularisation methods.
problem Improving performance of multimodal systems with multiple objectives and regularisation.
method Introduces a second objective over multimodal fusion using variational inference and regularisation methods.
result Demonstrates potential for multiple objectives and probabilistic methods to lower variance and improve generalisation.
Bayesian VFLMSP improves multimodal survival prediction with privacy.
problem Privacy and reliability in multimodal time-to-event prediction.
method Bayesian Vertical Federated Learning (VFL) with differential privacy.
result Consistent improvements in C-index compared to existing methods.
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…
Dp-CLIP preserves privacy in multimodal AI training.
problem Privacy concerns in multimodal AI, especially in vision-language tasks.
method Differentially private adaptation of CLIP model.
result Dp-CLIP retains accuracy while ensuring privacy.
Develops a deep multimodal classifier for medical images and reports.
problem Challenges of small datasets in medical deep learning.
method Transfer learning, integrated gradients, unsupervised clustering, tuning parameter.
result Improves classification accuracy by 4% and 7% on average.
Deep learning predicts mental disorders from audio and text samples.
problem Predicting mental disorders from speech samples.
method Multimodal deep learning structure using various pre-trained models for audio and text embeddings, transfer learning, and auxiliary corpora.
result Acceptable accuracy in predicting mental disorders through multimodal analysis.
FMT model improves multimodal sequential learning across language, vision, and acoustic data.
problem Modeling spatio-temporal dynamics across multiple modalities.
method Factorized Multimodal Transformer (FMT) that models intramodal and intermodal dynamics in a factorized manner.
result FMT outperforms existing models on 3 datasets and 21 labels, setting new state of the art.
Evidential Softmax preserves multimodality in sparse probability distributions for generative models.
problem Sparse probability distributions in deep generative models make exact marginalization computationally intractable.
method Introduce ev-softmax, a sparse normalization function that preserves multimodality and can be trained with probabilistic loss functions.
result ev-softmax outperforms existing techniques in distributional accuracy and dimensionality reduction.
lamBERT learns language and actions using multimodal BERT.
problem Learning language and actions in complex environments.
method Extending BERT to multimodal representation and integrating with reinforcement learning.
result lamBERT model achieved higher rewards in multitask and transfer settings.
Hybrid model for multimodal distributions using diffusion and classification.
problem Sampling from multimodal distributions with correct proportions.
method Divide-and-conquer strategy: identify modes, train classifiers, diffusion models, bridge sampling.
result Framework effectively handles multimodal distributions in high dimensions.
Proposes a method to improve SLMC for multimodal distributions.
problem Difficulty of applying SLMC to multimodal distributions.
method Parallel adaptive annealing with VAE-SLMC.
result Can proficiently obtain accurate samples from multimodal distributions.
New model learns multimodal data better than DAGs.
problem Complex multimodal data not well captured by DAGs.
method Latent partial causal model with two latent coupled variables.
result Identifiability result shows representations correspond to latent variables.
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.
Filtering data with a pre-trained model improves multimodal contrastive learning performance.
problem Improving the quality of internet-scale multimodal datasets.
method Characterized the performance of filtered contrastive learning under a bimodal data generation model.
result Data filtering using a pre-trained model reduces contrastive learning error by a factor of η \sqrt{η} η in the large η η η regime. We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder takes multimodal data as input and fuses them to a latent space representa…
Training-free method improves text-to-image generation quality.
problem Error accumulation in simultaneous token updates of masked diffusion models.
method Training-free self-correction framework exploiting inductive biases.
result Significantly improved generation quality on text-to-image tasks.
MMAML adapts quickly to multimodal tasks with task-aware modulation.
problem Limitation of common initialization in MAML for diverse task distributions.
method Augment MAML with task-aware modulation to adapt to multimodal task distributions.
result MMAML improves adaptation efficiency on multimodal few-shot learning tasks.
A new GAN model LDAGAN uses Latent Dirichlet Allocation to model multimodal images.
problem Ignoring the structure and multimodal characteristics of vision data in GANs.
method Introduced a Dirichlet prior for multimodal image generation leading to LDAGAN. LDAGAN defines generative modes for each sample and uses a VEM algorithm for adversarial training.
result Experimental results show LDAGAN outperforms other GANs on real-world datasets.
AECF improves multimodal inference robustness and calibration.
problem Robustness and calibration issues in multimodal systems with missing inputs.
method Adaptive Entropy-Gated Contrastive Fusion (AECF) layer.
result Improves masked-input mAP by +18 pp at a 50% drop rate.
A new objective function using Jensen-Shannon divergence improves generative learning from multiple data types.
problem Learning from multiple data types efficiently and accurately.
method Proposes a novel objective function using Jensen-Shannon divergence to approximate multimodal posteriors directly.
result The mmJSD objective optimizes an ELBO and improves generative learning tasks.
Proposes a multimodal deep generative model for semi-supervised learning with class imbalance.
problem Class imbalance in semi-supervised learning with partial supervision.
method Separate encoders for each modality, sharing latent variables, and using Student's t-distributions for prior, encoder, and decoder.
result Outperforms baseline methods in generalization and classification performance for partially labeled multimodal data.
Open-FinLLMs tackle financial tasks with multimodal capabilities.
problem Financial LLMs lack multimodal capabilities and real-world applicability.
method Developed Open-FinLLMs, an open-source multimodal financial LLM suite.
result Open-FinLLMs outperform advanced financial and general LLMs in diverse tasks.
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.
Quantized-TinyLLaVA reduces communication costs in split learning for multimodal models.
problem High communication costs in split learning for multimodal models.
method Integrates a compression module that quantizes intermediate features into discrete representations before transmission.
result Achieves an approximate 87.5% reduction in communication overhead with 2-bit quantization.
New method for multi-modal depth prediction challenges.
problem Challenges in applying unimodal coreset selection to multi-modal data.
method Adapted state-of-the-art coreset selection technique for multimodal data.
result Challenges in extending unimodal algorithms to multi-modal scenarios.
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.
WebGUM learns web navigation from multimodal data, outperforming previous methods.
problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.
Method retrieves similar fashion items from images and text, enabling style refinement.
problem Lack of intuitive, interactive refinement in search engines for fashion items.
method Joint visual-textual embedding training, Mini-Batch Match Retrieval, attribute extraction.
result Improved performance in multimodal style search, demonstrated through benchmark.
DECAT framework evaluates multimodal models for shared biology, detecting confounders and false positives.
problem Determining if multimodal models learn shared biology or just confounders.
method DECAT framework classifies multimodal representations into four diagnostic scenarios using null-referenced metrics.
result DECAT detects confounders and false positives in multimodal models, improving with larger cohorts and stronger representations.
Paper proposes ICCN to learn correlations between text, audio, and video for multimodal sentiment analysis.
problem Improving multimodal sentiment analysis by learning hidden correlations between text and audio/video features.
method Interaction Canonical Correlation Network (ICCN) using deep canonical correlation analysis (DCCA).
result Empirical results confirm the effectiveness of ICCN in capturing useful information from all three views.
PNNs improve treatment outcomes in TAVR and liver trauma.
problem Improving treatment outcomes in medical procedures.
method Multimodal Prescriptive Neural Networks (PNNs) combining optimization and machine learning.
result PNNs significantly improve estimated outcomes in medical procedures.
A new mutual information lower bound for multimodal regression active learning.
problem Lack of effective acquisition functions for multimodal regression active learning.
method Introduces a Two-Index framework for separating epistemic and aleatoric sources of uncertainty, deriving MI-LB as a closed-form approximation.
result MI-LB consistently outperforms baselines on multimodal regression tasks.
Fidel-TS creates a new benchmark for time series forecasting models.
problem Lack of high-quality benchmarks for time series forecasting models.
method Formalized high-fidelity benchmark principles, including data sourcing integrity, leak-free design, and structural clarity. Created Fidel-TS, a new large-scale benchmark.
result Demonstrated the limitations of prior benchmarks and potential discrepancies in model evaluation.
AACE learns treatment policies from EHRs using annotations to improve accuracy.
problem Learning treatment policies from multimodal EHRs with bias and inefficiency.
method Annotation-assisted coarsened effects (AACE) method.
result AACE outperforms existing methods in predicting treatment benefit from multimodal EHRs.
Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly, one parametrizes a transition operator for a Markov chain whose stationary distribution is an estimator of the data generating distributio…
This study compares two methods for sampling with transport maps, finding flow-based proposals work better for multimodal distributions.
problem Sampling from distributions with complex geometries.
method Compares two approaches: (i) proposal draws from the flow and (ii) reparametrization.
result Flow-based proposals are more effective for multimodal distributions in high dimensions, while reparametrization methods are more robust in other scenarios.
Graph-based multimodal federated learning for HAR improves accuracy and privacy.
problem Challenges in HAR due to noisy data, incomplete measurements, and privacy concerns.
method Proposes GraMFedDHAR, a Graph-based Multimodal Federated Learning framework for HAR tasks, using modality-specific graphs, residual GCNs, and attention-based fusion.
result Experimental results show up to 13 percent performance improvement for MultiModalGCN under differential privacy constraints.
Bayesian neural networks benefit from fully marginalizing over all modes to improve generalization.
problem Bayesian neural networks suffer from multimodal posterior distributions that can lead to suboptimal generalization.
method Use appropriate Bayesian sampling tools to fully marginalize over all posterior modes.
result Training with full marginalization improves the ability of the network to reason between multiple candidate solutions.
Multimodal deep learning improves toxicity prediction accuracy.
problem Improving prediction accuracy of chemical compound toxicity.
method Combining multiple neural network types and data representations.
result Significantly better accuracy on a toxicity benchmark.
This paper investigates uncertainty calibration in multimodal large language models.
problem Challenges in properly calibrating uncertainty in multimodal large language models.
method Investigation of representative MLLMs across various scenarios, including visual fine-tuning and multimodal training.
result MLLMs tend to give answers rather than admit uncertainty, but this self-assessment improves with proper prompt adjustments.
New deep fusion methods improve human action recognition using depth and inertial sensor data.
problem Existing multimodal HAR frameworks lack mid-level feature fusion.
method Proposes three deep multilevel multimodal fusion frameworks, transforming depth and inertial sensor data into images and using convolution with Prewitt filter to create modality within modality.
result Supremacy of proposed fusion frameworks over existing methods on three publicly available datasets.
Paper analyzes biases in video QA datasets, showing models can answer 37-48% questions correctly without multimodal context.
problem Question answering biases in video QA datasets can lead to model overfitting and poor generalization.
method Analyzed popular video question answering datasets, conducted ablation studies on biases from annotators and question types.
result Pretrained language models can answer 37-48% questions correctly without multimodal context, far exceeding random guess baseline.
Enhances hand gesture recognition with separate networks and shared features.
problem Improving recognition accuracy of unimodal 3D-CNNs for dynamic hand gestures.
method Separate networks for each modality, collaborative learning, spatiotemporal semantic alignment loss, focal regularization.
result Improves test time recognition accuracy and state-of-the-art performance.
Push-forward models struggle to fit multimodal distributions due to high Lipschitz constants.
problem Expressivity of push-forward generative models in fitting multimodal distributions.
method Analyzing the Lipschitz constant and its relation to the total variation distance and Kullback-Leibler divergence.
result Push-forward models require high Lipschitz constants to approximate multimodal distributions, leading to a trade-off between expressivity and stability.
AMA-LSTM improves stock volatility prediction using adversarial training.
problem Predicting stock volatility from financial audio data is challenging due to stochasticity and bias.
method Adversarial training to generate perturbations that simulate stochasticity and bias.
result AMA-LSTM outperforms state-of-the-art methods in predicting stock volatility.
Bayesian neural networks reveal multimodal predictive distributions.
problem Uncertainty quantification and interpretability in neural networks.
method Discretized prior for inner layer weights, Gaussian mixture approximation of posterior predictive distribution.
result Distinct parameter realizations can produce the same training error but different posterior predictive distributions.