Research map / Video / Video segmentation and tracking
Learning to Factorize Spatio-Temporal Foundation Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces FactoST, a factorized spatio-temporal foundation model that decouples universal temporal pretraining from spatio-temporal adaptation to avoid costly joint pretraining.
Problem
Spatio-temporal foundation models (STFMs) aim for zero/few-shot generalization across datasets, but joint spatio-temporal pretraining is computationally prohibitive and struggles with domain-specific spatial correlations.
Approach
Factorizes STFM training into two stages: first pretrain a space-agnostic temporal backbone, then adapt it to spatio-temporal settings, decoupling universal temporal pretraining from spatial adaptation.
Closest papers by meaning
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (NeurIPS 2025 · similarity 0.88)
- Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model (NeurIPS 2024 · similarity 0.88)
- FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting (ICML 2025 · similarity 0.87)
- Learning from Highly Sparse Spatio-temporal Data (NeurIPS 2024 · similarity 0.87)
- STD-PLM: Understanding Both Spatial and Temporal Properties of Spatial-Temporal Data with PLM (AAAI 2025 · similarity 0.87)
- ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.