ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset
cs.RO
Submitted: 2026-11-08
Updated: 2026-11-08
Project page: https://nus-lins-lab.github.io/ObjectWorld
Terminology
Sources
- OpenVLA: An Open-Source Vision-Language-Action Model
- World Model for Robot Learning: A Comprehensive Survey
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
- ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos
- Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulation
- NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
- Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
- Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction
- On the effectiveness of task granularity for transfer learning
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
- Depth Anything 3: Recovering the Visual Space from Any Views
- Advancing Complex Video Object Segmentation via Progressive Concept Construction
- SAM 3D: 3Dfy Anything in Images
- Qwen2.5-VL Technical Report
- ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
- Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
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