EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper
•
2508.21112
•
Published
•
77
Papers
-
-
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
Paper • 2508.05635 • Published • 73 -
Hume: Introducing System-2 Thinking in Visual-Language-Action Model
Paper • 2505.21432 • Published • 4 -
Is Diversity All You Need for Scalable Robotic Manipulation?
Paper • 2507.06219 • Published • 20 -
EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
Paper • 2505.09694 • Published • 19 -
EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation
Paper • 2501.01895 • Published • 55 -
EnerVerse-AC: Envisioning Embodied Environments with Action Condition
Paper • 2505.09723 • Published • 23 -
AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
Paper • 2503.06669 • Published • 2 -
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning
Paper • 2503.11646 • Published • 34 -
UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
Paper • 2505.06111 • Published • 25 -
Act2Goal: From World Model To General Goal-conditioned Policy
Paper • 2512.23541 • Published • 21 -
GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training
Paper • 2509.24494 • Published • 10