Learning Robotic World Models with Semantic and Visual Feedback
cs.RO, cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/SoMarkAI/mJev
Terminology
Sources
- World Models
- World Model for Robot Learning: A Comprehensive Survey
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Evaluating Real-World Robot Manipulation Policies in Simulation
- Thinking in Video: Can Video Generators Really Reason About the Real World?
- WorldModelBench: Judging Video Generation Models As World Models
- RLVR-World: Training World Models with Reinforcement Learning
- Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
- Vid2World: Crafting Video Diffusion Models to Interactive World Models
- Robot Learning from a Physical World Model
- FutureWorlds: Learning Robotic World Models from Alternative Futures
- RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
- Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- RoboDreamer: Learning Compositional World Models for Robot Imagination
- IRASim: A Fine-Grained World Model for Robot Manipulation
- VideoGPT: Video Generation using VQ-VAE and Transformers
- Cosmos World Foundation Model Platform for Physical AI
- Deep multi-scale video prediction beyond mean square error
- PhyCritic: Multimodal Critic Models for Physical AI
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation