LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
cs.LG, cs.AI
Submitted: 2026-08-30
Updated: 2026-08-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
- Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
- HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
- Time Series as Images: Vision Transformer for Irregularly Sampled Time Series
- UrbanGPT: Spatio-Temporal Large Language Models
- Multi-Time Attention Networks for Irregularly Sampled Time Series
- TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
- Graph WaveNet for Deep Spatial-Temporal Graph Modeling
- FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks