DreamX: Video Diffusion Model is a Universal Latent Action Learner
cs.CV, cs.AI, cs.RO
Submitted: 2026-11-03
Updated: 2026-11-03
Project page: https://cvlab-kaist.github.io/DreamX
Terminology
Sources
- World Simulation with Video Foundation Models for Physical AI
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- MolmoAct2: Action Reasoning Models for Real-world Deployment
- AdaWorld: Learning Adaptable World Models with Latent Actions
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
- How Much 3D Do Video Foundation Models Encode?
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- OpenVLA: An Open-Source Vision-Language-Action Model
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos
- LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
- Latent Action Learning Requires Supervision in the Presence of Distractors
- mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
- EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
- VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
- Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
- ZeroFlow: Scalable Scene Flow via Distillation
- From Image to Video: An Empirical Study of Diffusion Representations
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