Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/ztxtech/fracast-0
Terminology
Sources
- GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
- Chronos-2: From Univariate to Universal Forecasting
- KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
- Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
- Toto 2.0: Time Series Forecasting Enters the Scaling Era
- Moirai 2.0: When Less Is More for Time Series Forecasting
- TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
- GLU Variants Improve Transformer
- Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model
- Into the ORBIT for Time Series: Training Regimes for Foundation Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection