EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
cs.CV, cs.RO
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/Genesis-Embodied-AI/genesis-world
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
- PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects
- DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation
- UniWAM: Unified World-Action Model
- DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
- OpenVLA: An Open-Source Vision-Language-Action Model
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
- UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets
- HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
- PAct: Part-Decomposed Single-View Articulated Object Generation
- From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
- HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation
- RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation
- SAM 3D: 3Dfy Anything in Images
- GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
- EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence
- EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
- ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
- 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
- PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models