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…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,042 papers · 148 categories
Trend · papers per month
48 results for “interaction modalities”
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.
A novel multi-modal active learning approach using RL for engagement estimation.
problem Challenges in labeling multi-modal human data for accurate user state estimation.
method Deep reinforcement learning for optimal data selection and multi-modal data fusion.
result The proposed approach outperforms existing methods in engagement estimation.
Improved sentiment analysis with multimodal data.
problem Cross-modal sentiment analysis in social media, customer service, and video blogs.
method Gated mechanism for attention-based learning of cross-modal interactions, with experiments on CMU-MOSI and CMU-MOSEI datasets.
result 1.6% and 1.34% absolute improvement over state-of-the-art.
Proposes a method to improve urban spatiotemporal forecasting using multi-modal graph interaction.
problem Improving spatiotemporal forecasting in urban areas using graph convolution networks.
method Develops modality interaction mechanisms for multi-graph convolution networks to reduce generalization error.
result Proposed techniques improve prediction accuracy and model robustness compared to state-of-the-art baselines.
Efficient video captioning model captures cross-modal interactions.
problem Capturing frame-level cross-modal interactions in video captioning.
method Proposes High-Order Cross-Modal Attention (HOCA) and Low-Rank HOCA.
result Low-Rank HOCA achieves state-of-the-art performance.
Integrates MRF into multimodal VAE for better complex intermodal interactions.
problem Lack of effective modeling of complex intermodal interactions in multimodal VAEs.
method Incorporates Markov Random Field into prior and posterior distributions of multimodal VAE.
result Demonstrates superior performance in managing complex intermodal dependencies.
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…
Paper proposes a multi-modal probabilistic prediction model for interactive behavior.
problem Predicting future motions of interacting entities in real-world scenarios.
method Generative model for joint prediction of sequential motions of interacting agents.
result Interpretable model capable of handling prediction uncertainties and multi-modal distributions.
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
problem Detecting anomalies in attributed networks where structure and attributes interact.
method Dual autoencoder framework with attention mechanism for joint learning of structure and attribute embeddings.
result AnomalyDAE effectively detects anomalies by reconstructing node attributes and structures.
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.
ESE-FN improves elderly activity recognition accuracy.
problem Recognizing individual actions and human-object interactions in elderly activities.
method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.
result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.
Robots learn intentions from multiple cues to reduce uncertainty.
problem Uncertainty in human-robot interaction for vulnerable users.
method Multimodal classifier fusion using Bayesian Independent Opinion Pool.
result Fused classifiers outperform individual modalities in accuracy and uncertainty reduction.
EMDE efficiently estimates manifold densities for diverse recommendation systems.
problem Efficiently estimating manifold densities for multi-modal recommendation systems.
method EMDE (Efficient Manifold Density Estimator) framework for arbitrary vector representations.
result Established new state-of-the-art results in top-k and session-based recommendation settings.
Proposes a new model to capture interaction modalities in networks.
problem Limited information in binary network representations of interactions.
method Topic Blockmodel using a count-based topic model.
result Better extraction of information from interaction networks.
Estimates interactions between modalities for multimodal data.
problem Accurately quantifying interactions between different data types.
method Developed Lightweight Sample-wise Multimodal Interaction (LSMI) estimator using pointwise information theory.
result LSMI reveals fine-grained dynamics in multimodal data.
This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.
problem Measuring and ranking uncertainty in multi-agent multi-modal trajectory forecasting.
method Proposes collaborative uncertainty (CU) and a CU-aware regression framework.
result The CU-aware regression framework improves SOTA systems' performances.
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.
Investigating Audio, Visual, and Text Fusion Methods for End-to-End Automatic Personality Predictioncs.AI
We propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video data. For each channel, stacked Convolutional Neural Networks are employed. The channels are fused both on decision-level and by concatenating their respective fully conne…
A method uses autoencoders to align multi-modal neuron data.
problem Inconsistent cell type definitions across different data modalities.
method Coupled training of autoencoders for cross-modal alignment.
result Representations learned by coupled autoencoders can identify single-modality sampled cell types.
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.
CF-VAE models capture multi-modal distributions for better structured sequence prediction.
problem Challenges in capturing multi-modality of future states in latent variable models.
method Conditional Flow Variational Autoencoders (CF-VAE) with conditional normalizing flows.
result CF-VAE achieves state-of-the-art results on multi-modal structured sequence prediction datasets.
Study reveals efficient recovery of multi-modal signals via Bayesian methods and sequential learning.
problem Recovering multiple high-dimensional signals from correlated modalities.
method Bayesian Approximate Message Passing and Sequential Curriculum Learning.
result Sequential learning strategy optimally recovers weak signals in multi-modal settings.
Remembering our day-to-day social interactions is challenging even if you aren't a blue memory challenged fish. The ability to automatically detect and remember these types of interactions is not only beneficial for individuals interested in their behavior in crowded situations, but also of interest to those who analyz…
New methods for Bayesian inference using mean shift particle systems.
problem Approximating expectations with unnormalized densities in Bayesian inference.
method Mean shift interacting particle systems that minimize maximum mean discrepancy (MMD).
result Mean shift interacting particle systems converge quickly and capture complex distributions.
This paper uses robust optimization to analyze supply chain resilience.
problem Supply chain resilience analysis of multi-modal logistics networks.
method Robust optimization with budget-of-uncertainty.
result Interactive effects of network size, disruption scale, and degree on resilience.
FININ predicts financial markets by modeling news interactions and influence.
problem Complex diffusion of financial news into market prices.
method FININ is a novel model that captures news links and interactions, integrating market data and news articles.
result FININ outperforms advanced models with a 0.429 and 0.341 improvement in daily Sharpe ratio for S&P 500 and NASDAQ 100 respectively.
Taxonomy of knowledge modalities in RL for better transfer.
problem Tackling the transfer of knowledge in reinforcement learning.
method Systematic analysis of knowledge modalities in RL.
result A taxonomy of knowledge modalities in reinforcement learning.
MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Tradingq-fin.TR
MountainLion uses LLMs to interpret financial data and generate investment strategies.
problem Challenges in integrating heterogeneous data for financial trading.
method Multi-modal LLM-based agents that process textual and visual data.
result Improves returns and investor confidence through interpretable investment framework.
AttentionDDI: Siamese Attention-based Deep Learning method for drug-drug interaction predictionsq-bio.QM
A neural network predicts drug interactions using attention mechanisms.
problem Predicting drug-drug interactions from massive combinations of drugs.
method Siamese self-attention multi-modal neural network integrating drug characteristics.
result The model achieves AUPR scores ranging from 0.77 to 0.92 on various benchmark datasets.
Active authentication is the problem of continuously verifying the identity of a person based on behavioral aspects of their interaction with a computing device. In this study, we collect and analyze behavioral biometrics data from 200subjects, each using their personal Android mobile device for a period of at least 30…
A new framework quantifies how model explanations influence each other.
problem Understanding how different model explanations interact and influence each other.
method Introducing the metagame, a conceptual framework for measuring second-order interaction effects of model explanations using Shapley values.
result Meta-attributions provide directional insights into how feature interactions influence model explanations.
KHGRec tackles noisy and incomplete KG-enhanced recommendations by modeling complex interactions.
problem Challenges in integrating KGs for accurate recommendations, especially in complex higher-order interactions and heterogeneous modalities.
method KHGRec uses a collaborative knowledge heterogeneous hypergraph (CKHG) to model group-wise interdependencies, employing two hypergraph encoders and attention mechanisms.
result KHGRec achieves an average 5.18% relative improvement over state-of-the-art baselines on four real-world datasets.
Enhances disease progression modeling using LLMs for complex brain connectivity.
problem Inaccurate predictions of disease spread due to oversimplified brain connectivity models.
method Uses LLMs to synthesize multi-modal relationships and learn disease trajectories from longitudinal data.
result Superior prediction accuracy and interpretability compared to traditional methods.
In this paper, we explore salient questions about user interests, conversations and friendships in the Facebook social network, using a novel latent space model that integrates several data types. A key challenge of studying Facebook's data is the wide range of data modalities such as text, network links, and categoric…
This research integrates human interaction into reinforcement learning to improve sample efficiency and real-time learning.
problem Current reinforcement learning requires thousands of samples to converge, and is prone to catastrophic failures.
method Integrates human interaction modalities (demonstrations, interventions, evaluations) into the reinforcement learning loop.
result Human interaction accelerates learning and improves sample efficiency.
Large language models predict human sensory judgments across multiple modalities.
problem Determining the extent of perceptual information in language.
method State-of-the-art large language models were used to predict sensory judgments across six psychophysical datasets.
result Large language models can predict human sensory judgments across multiple modalities with significant correlation to human data.
Paper introduces a method for generating interlocutor-aware facial gestures in dyadic settings.
problem Generating appropriate non-verbal behavior for conversational agents in dyadic settings.
method Probabilistic method using multi-modal cues from the interlocutor to synthesize facial gestures.
result The model successfully leverages multi-modal input from the interlocutor to generate more appropriate behavior.
Adaptive anchor methods improve multi-modal learning by balancing intra-modal and inter-modal information.
problem Fixed anchor methods limit multi-modal learning by over-reliance on a single modality and inadequate cross-modal correlation.
method Adaptive anchor methods using centroid-based anchors from all modalities.
result Adaptive anchor methods like CentroBind consistently outperform fixed anchor methods across various datasets.
DVAO predicts volumetric ambient occlusion for real-time volume rendering.
problem Predicting per-voxel ambient occlusion in volumetric data sets.
method Deep learning neural network that considers global information through transfer function.
result DVAO supports real-time volume interaction and generalizes to various modalities.
KD-Net transfers knowledge from multi-modal to mono-modal segmentation networks.
problem Limited acquisition of multiple imaging modalities in clinical settings.
method Generalized distillation framework adapted for mono-modal networks.
result The student network outperforms baseline mono-modal networks in brain tumor segmentation.
A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. We present an analysis of the role that multiplicative interactions play in learning such …
MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learningcs.LG
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.
The paper analyzes and proposes an algorithm for multi-modal nonlinear embeddings with theoretical performance bounds.
problem Generalizability of multi-modal nonlinear embeddings to unseen data.
method Theoretical analysis and a multi-modal nonlinear representation learning algorithm motivated by performance bounds.
result The proposed algorithm yields promising performance in multi-modal image classification and cross-modal image-text retrieval applications.
MOTGNN integrates multi-omics data for disease classification with improved accuracy and interpretability.
problem Challenges in integrating multi-omics data due to high dimensionality, heterogeneity, and lack of reliable interaction networks.
method MOTGNN uses XGBoost for graph construction, modality-specific GNNs for representation learning, and a deep feedforward network for cross-omics integration.
result MOTGNN outperforms state-of-the-art baselines by 5-10% in accuracy, ROC-AUC, and F1-score across three real-world disease datasets.
MMVAE learns multi-modal data with shared and private latent spaces.
problem Learning useful representations across multiple data modalities.
method Mixture-of-experts variational autoencoder (MMVAE).
result MMVAE satisfies four criteria for multi-modal learning.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
MCC algorithm predicts with partial modalities, outperforming full modalities.
problem Predicting with inconsistent and diverse multi-modal data.
method Instance-oriented Multi-modal Classifier Chains (MCC) algorithm.
result MCC outperforms full modalities in prediction.