Dynamics-Informed Action Learning for Goal-Conditioned Latent Planning
cs.CV, cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Fast LeWorldModel
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Diverse Domains through World Models
- Training Agents Inside of Scalable World Models
- Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesis
- World Model Control by Trajectory Reachability Metrics
- Predictive but Not Plannable: RC-aux for Latent World Models
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Transformers are Sample-Efficient World Models
- Latent Geometry Beyond Search: Amortizing Planning in World Models
- Player-1: Learning to Play from Synthetic Experience
- Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Inference
- Joint Embedding Predictive Architectures Focus on Slow Features
- INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models
- DeepMind Control Suite
- TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
- PRISM: PRior-guided Imagination Sampling in world Models
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs