sigma-LeWM: Learning World Models via S-Information for Robot Control
cs.LG, cs.AI, cs.RO
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- World Action Models are Zero-shot Policies
- Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
- Auto-Encoding Variational Bayes
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
- Predictive but Not Plannable: RC-aux for Latent World Models
- Sensorimotor World Models: Perception for Action via Inverse Dynamics
- Latent Geometry Beyond Search: Amortizing Planning in World Models
- ACID: Action Consistency via Inverse Dynamics for Planning with World Models
- Representation Learning with Contrastive Predictive Coding
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