embodied ai
A field of AI that focuses on integrating AI agents within physical bodies, allowing them to interact and learn from real-world environments. It emphasizes the role of physical presence in AI learning and decision-making.
- ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
- DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
- Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
- Emerging Risks from Embodied AI Require Urgent Policy Action
- HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
- InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
- Learning Interactive World Model for Object-Centric Reinforcement Learning
- Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
- Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
- TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
- TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
- Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
- Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
- Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
- URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
- What Can RL Bring to VLA Generalization? An Empirical Study