An Evaluation of Tabular Foundation Models as Training-Free World Models
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- World Models
- World Action Models: The Next Frontier in Embodied AI
- One-shot World Models Using a Transformer Trained on a Synthetic Prior
- From system models to class models: An in-context learning paradigm
- On Foundation Models for Dynamical Systems from Purely Synthetic Data
- Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks
- ICR-RL: Deep Reinforcement Learning via In-Context Regression
- TabQL: In-Context Q-Learning with Tabular Foundation Models
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Cosmos World Foundation Model Platform for Physical AI
- Neural Context Flows for Meta-Learning of Dynamical Systems
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis