Generates multimodal safety-critical scenarios for robustness evaluation of decision-making algorithms.
problem Lack of comprehensive evaluation of neural network robustness under real-world scenarios.
method Proposes a flow-based multimodal scenario generator using weighted likelihood maximization and gradient-based sampling.
result Demonstrates improved testing efficiency and multimodal modeling capability compared to traditional methods.
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.
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.
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.
UniFinEval benchmarks financial models across text, images, and videos.
problem Challenges in evaluating financial multimodal models across text, images, and videos.
method Proposes UniFinEval, a unified multimodal benchmark for financial scenarios.
result Gemini-3-pro-preview achieves best performance but still lags behind experts.
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…
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…
Characterizing the dynamic interactive patterns of complex systems helps gain in-depth understanding of how components interrelate with each other while performing certain functions as a whole. In this study, we present a novel multimodal data fusion approach to construct a complex network, which models the interaction…
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.
VLM judges rank well but score poorly; task difficulty and annotation quality affect interval width.
problem VLMs as judges lack reliability indicators in multimodal evaluations.
method Conformal prediction using score-token log-probabilities.
result Evaluation uncertainty is task-dependent, affecting interval width and reliability.
Proposes neural network for causal inference with multimodal data.
problem Estimating causal effects with text and image data as confounders.
method Double machine learning framework adapted to partially linear models, semi-synthetic dataset generation.
result Improved performance in causal effect estimation with multimodal data.
In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative f…
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.
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.
Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides supervision for disentangling the underlying explanatory factors of each modality. Previ…
RandomNet uses random search to design neural architectures without much human intervention.
problem Designing neural architectures without excessive human intervention.
method Random search strategy for multimodal neural architecture design.
result RandomNet performs close to state-of-the-art on AV-MNIST with minimal human supervision.
Study improves stock movement prediction using multimodal data.
problem Inaccurate stock movement prediction due to incomplete multimodal data integration.
method Introduces MSGCA framework for robust multimodal fusion.
result MSGCA framework outperforms existing methods by 21.7% on multimodal datasets.
This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an intermediate representation based on a combination of data from different modalities. Th…
Unified framework explains few-shot multimodal medical imaging performance.
problem Limited labeled data in rare diseases and low-resource settings.
method PAC learning, VC theory, PAC Bayesian analysis, information gain, Chain of Thought reasoning.
result Unified theoretical framework for few-shot multimodal medical imaging.
MHVAE learns cross-modality inference inspired by human cognition.
problem Cross-modality inference in multimodal data.
method Hierarchical multimodal generative model with modality-specific and joint-modality distributions.
result MHVAE performs on par with state-of-the-art models on multimodal datasets.
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.
In this paper we seek methods to effectively detect urban micro-events. Urban micro-events are events which occur in cities, have limited geographical coverage and typically affect only a small group of citizens. Because of their scale these are difficult to identify in most data sources. However, by using citizen sens…
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.
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.
Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on simple link structure between a finite set of entities, ignoring the variety of data types that are often used in knowledge bases, such as text, …
Benchmarking AutoML for tables with text fields, achieving top performance.
problem Evaluating automated learning systems for tables with text fields.
method Publicly available benchmark with 18 datasets varying in size, types, and feature composition.
result Stack ensembling a multimodal Transformer with various tree models achieved top performance.
Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiti…
Graph Mixture Density Networks model multimodal data on graphs.
problem Challenging conditional density estimation problems with structured data.
method Combining mixture models and graph representation learning.
result Significant improvement in likelihood of epidemic outcomes.
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.
Stacking improves inference for multimodal Bayesian posterior distributions.
problem Difficulty of MCMC in moving between modes and underestimation of posterior uncertainty.
method Parallel runs of MCMC, variational, or mode-based inference, combined using Bayesian stacking.
result Stacking efficiently samples from multimodal posterior distributions and represents uncertainty better than variational inference.
ICYM2I corrects missingness bias in multimodal learning.
problem Missingness patterns between source and target environments affect multimodal learning performance.
method ICYM2I uses inverse probability weighting to correct missingness bias in predictive performance and information gain.
result ICYM2I improves multimodal learning performance by accounting for missingness.
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.
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better cla…
Study proposes a multimodal model for cardiovascular risk prediction using EHRs.
problem Lack of comprehensive risk prediction from EHRs due to unstructured text.
method Proposes a multimodal BiLSTM model integrating structured and unstructured EHR data.
result Proposed BiLSTM model outperforms other DNN architectures in cardiovascular risk prediction.
Hybrid method improves sampling from multimodal distributions.
problem Sampling from multimodal posterior distributions efficiently.
method Jump-Diffusion Langevin Dynamics hybrid with Metropolis.
result Calibrated hybrid method outperforms pure methods.
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.
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.
Clustering is an essential data mining tool that aims to discover inherent cluster structure in data. As such, the study of clusterability, which evaluates whether data possesses such structure, is an integral part of cluster analysis. Yet, despite their central role in the theory and application of clustering, current…
Multimodal analysis assesses job interview performance and provides feedback.
problem Assessing candidate performance in interviews for professional roles.
method Multimodal analytical framework using video, audio, and text data.
result The proposed methodology achieved promising results in predicting behavioral cues.
Unified model predicts stock and systemic risks from diverse financial data.
problem Isolating financial tasks leads to missed cross-scale dependencies.
method Shared Transformer backbone with modular task heads for cross-modal attention and multi-task optimization.
result Uni-FinLLM significantly outperforms baselines in stock forecasting, credit-risk assessment, and systemic-risk detection.
DDSME outperforms SME in estimating multimodal distributions.
problem Efficiency of score matching in multimodal distributions.
method Diffusion-based denoising score matching (DDSME) compared to vanilla score matching (SME).
result DDSME avoids the error bound deterioration of SME with increasing mode separation.
Paper proposes a capsule attention mechanism for EEG-EOG vigilance estimation.
problem Driver vigilance estimation for safer transportation.
method Capsule attention mechanism following LSTM network for multimodal EEG-EOG analysis.
result Capsule attention improves vigilance estimation robustness and accuracy.
Framework detects anomalies in industrial processes using deep learning.
problem Detect anomalies in complex industrial processes.
method Causal-based framework with unsupervised deep learning.
result Successfully validated abstract contexts of blast furnace assets.
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.
CDS combines PT and diffusion for efficient sampling from multimodal distributions.
problem Sampling from unnormalized multimodal distributions efficiently.
method Conditional Diffusion Sampling (CDS) using Conditional Interpolants and Parallel Tempering.
result CDS achieves a superior trade-off between sample quality and density evaluation cost.
Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate appealing performance on a variety of domains such as few-shot image classificat…
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…
An infinite parallel tempering bouncy particle sampler improves sampling efficiency for multimodal distributions.
problem Sampling from complex posterior distributions with high accuracy and efficiency.
method Introduced an infinite parallel tempering bouncy particle sampler (BPS-PT) to accelerate convergence.
result Demonstrated improved sampling efficiency for multimodal distributions through numerical simulations.