FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-29

Comments: 25 pages, 12 figures. Project page: https://shidu-ren.github.io/FlexiWorld-Project-Page/

Project page: https://shidu-ren.github.io/FlexiWorld-Project-Page

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Hindsight Experience Replay
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• Revisiting Feature Prediction for Learning Visual Representations from Video
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
• Fast LeWorldModel
• Dream to Control: Learning Behaviors by Latent Imagination
• Temporal Difference Learning for Model Predictive Control
• Deep Reinforcement Learning that Matters
• Residual Reinforcement Learning for Robot Control
• Similarity of Neural Network Representations Revisited
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• Latent Geometry Beyond Search: Amortizing Planning in World Models
• DINOv2: Learning Robust Visual Features without Supervision

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks