Control-Geometry Straightening for Sampling-Based Latent Planning
cs.LG, stat.ML
Submitted: 2026-09-28
Updated: 2026-10-07
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Value-guided action planning with JEPA world models
- SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry
- Sensorimotor World Models: Perception for Action via Inverse Dynamics
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Causal-JEPA: Learning World Models through Object-Level Latent Masking
- INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models
- Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models
- AdaJEPA: An Adaptive Latent World Model
- Finite-Sample Closed-Loop Stability of Model Predictive Path Integral Control for Linear Time-Invariant Systems
- Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding
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