Research map / Multi-agent systems and games / Human-AI and goal-conditioned
X-World: Accessibility, Vision, and Autonomy Meet
Jimuyang Zhang, Minglan Zheng, Matthew Boyd, Eshed Ohn-Bar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune on X-World simulated data | COCO-pretrained Mask R-CNN · X-World Sim test (person/vehicle model) | AP: 35.1 -> 59.6 | Improved |
| fine-tune on X-World simulated data | Cityscapes-pretrained Mask R-CNN · X-World Sim test (person/vehicle model) | AP: 25.1 -> 60.0 | Improved |
| fine-tune on X-World simulated data | COCO-pretrained Mask R-CNN · X-World Sim test (person/vehicle model), person-wc class | AP: 8.9 -> 31.3 | Improved |
| COCO pretraining instead of Cityscapes | Mask R-CNN · X-World Sim test (person/vehicle model) | AP: 25.1 -> 35.1 | Improved |
| COCO pretraining instead of Cityscapes (after fine-tuning) | Mask R-CNN · X-World Sim test (person/vehicle model) | AP: 59.6 vs 60.0 | No clear effect |
| new mobility aids test setting added to test (ablation) | COCO & X-World (Sim) fine-grained · X-World Sim fine-grained 8 classes | AP: 43.9 -> 39.9 | Hurt |
| new weathers test setting added | COCO & X-World (Sim) fine-grained · X-World Sim fine-grained 8 classes | AP: 43.9 -> 43.7 | No clear effect |
| train on real data only vs simulation only | COCO & X-World · X-World Real-world benchmark | AP: 6.6 -> 29.8 | Improved |
| add simulated data to real training data | COCO & X-World (Real) · X-World Real-world benchmark, wc class | AP: 33.7 -> 36.1 | Improved |
| add simulated data to real training data | COCO & X-World (Real) · X-World Real-world benchmark, cane class | AP: 0.66 -> 1.83 | Improved |
| add simulated data to real training data | COCO & X-World (Real) · X-World Real-world benchmark, person-wc class | AP: 28.2 -> 30.3 | Improved |
| add simulated data to real training data | Cityscapes & X-World (Real) · X-World Real-world benchmark, cane class | AP: 0.70 -> 1.41 | Improved |
Closest papers by meaning
- Text to Blind Motion (NeurIPS 2024 · similarity 0.83)
- mmWalk: Towards Multi-modal Multi-view Walking Assistance (NeurIPS 2025 · similarity 0.82)
- Towards Autonomous Micromobility through Scalable Urban Simulation (CVPR 2025 · similarity 0.82)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.82)
- Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration (NeurIPS 2025 · similarity 0.82)
- CroCoDL: Cross-device Collaborative Dataset for Localization (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
