Predictive but Not Plannable: RC-aux for Latent World Models
cs.LG, cs.AI, cs.CV
Submitted: 2026-05-08
Updated: 2026-11-14
Comments: NeurIPS 2026
Code: https://github.com/Guang000/RC-aux
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Revisiting Feature Prediction for Learning Visual Representations from Video
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- MuDreamer: Learning Predictive World Models without Reconstruction
- Value-guided action planning with JEPA world models
- Learning to Reach Goals via Iterated Supervised Learning
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- OpenVLA: An Open-Source Vision-Language-Action Model
- Offline Reinforcement Learning with Implicit Q-Learning
- PcLast: Discovering Plannable Continuous Latent States
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- DINOv2: Learning Robust Visual Features without Supervision
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