Tag
TRACE is a multimodal framework that organizes daily clinical events (EHR, chest x-rays, radiology reports, discharge summaries) into temporal trajectories for inpatient risk prediction, achieving the highest AUROC across nine dataset-task settings on MIMIC-IV, eICU, and MIMIC-III cohorts.
这篇论文将音乐愉悦度预测构建为回归问题，利用MUSIN-G数据集的128通道EEG数据，比较了六种深度学习模型（DeepConvNet、CNN-LSTM、GNN-CNN、TCN等），并通过可解释性分析识别影响预测的关键时间片段。
This paper argues that LLMs' pretrained world knowledge is accessible for temporal event prediction when the interface is properly designed, introducing DescribeEvent (~150K events, 7 datasets) and showing that natural-language event descriptions plus symbolic labels let capable LLMs outperform specialized baselines.
The paper introduces CALIBRA, a calibration-first multimodal temporal framework for cross-cohort asthma risk forecasting that uses recurrent encoders, gradient-reversal domain adaptation, hierarchical logistic calibration, and conformal prediction to remain reliable under distribution shift and incomplete modalities, validated on a semi-synthetic three-cohort benchmark.
NeoTriFuse is a reliability-aware multimodal fusion framework for neonatal mortality risk prediction that explicitly models missing data as a reliability signal to dynamically modulate feature contributions, improving performance on incomplete clinical monitoring data.
ClockRoPE introduces random Fourier rotations to model temporal periodicity in sequential recommendation, theoretically grounded and validated via online A/B tests at a major video-sharing platform.
This paper presents an LLM-based pipeline for analyzing mental health changes from sequentially ordered social media posts, participating in the CLPsych 2026 shared task. It performs post-level assessment and user-level temporal modeling to capture shifts in psychological well-being.
The paper presents World Value Model (WVM), a generalist robotic value model that combines world models with value estimation to accurately assess task progression and improve robotic policy learning from mixed-quality data, achieving state-of-the-art results on standard benchmarks and a new suboptimal data benchmark.
This paper evaluates deep learning models (LSTM, TCN, Transformer) on the WESAD dataset for multimodal emotion recognition from physiological signals, showing that an ensemble achieves 98.91% accuracy.
Introduces Random Attention (RA), a lightweight temporal modeling module for mobile sleep staging that uses fixed random projections for similarity-based aggregation, achieving competitive performance with minimal additional parameters.
This paper proposes a rolling-window framework for customer churn prediction in non-contractual service environments, using 30-day behavioral windows to enable continuous risk assessment. Evaluated on real-world data, the feature-based model achieves 87.6% accuracy and 0.94 ROC-AUC, while the sequence-based model reaches 96.1% recall.
TBD-VLA introduces a discrete vision-language-action framework that combines block diffusion with autoregressive generation to achieve efficient temporal action modeling and faster inference, significantly outperforming prior VLA approaches in simulation and real-world manipulation tasks.
EvoMD-LLM reformulates reactive molecular dynamics trajectories as symbolic temporal sequences, enabling LLMs to model species evolution over time through fine-tuning and temporal scaffolding, achieving up to 66.14% accuracy and interpretable predictions.
This paper presents DreamerNLplus, a hybrid framework combining LLMs, DeBERTa, Random Forest, rule-based methods, and RAG to model mental health dynamics from social media timelines for the CLPsych 2026 shared task, achieving top rankings in subtasks for temporal summarization and change detection.
EEG-tGAT is a temporally augmented Graph Attention Network that improves affordance classification from interaction sequences by incorporating temporal attention and dropout mechanisms. The model enhances GATv2 for sequential data where temporal dimensions are semantically non-uniform.