temporal dependencies
Refers to the relationships and patterns that exist across different time points in sequential data. In AI, recognizing these dependencies is crucial for tasks like time series forecasting and natural language processing.
- A Pre-training Framework for Relational Data with Information-theoretic Principles
- Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction
- Approximating Shapley Explanations in Reinforcement Learning
- CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
- Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation
- Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
- Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
- InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
- InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
- Momentum Multi-Marginal Schrödinger Bridge Matching
- MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
- Neural Fractional Attention Differential Equations
- Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
- Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
- TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
- TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
- TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
- Unified Transferability Metrics for Time Series Foundation Models
- Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding