| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Depth Anything V2 | ✓ Link | 97.4 | Depth Anything V2 (ViT-G) | 2024-06-13 |
| In Pursuit of Pixel Supervision for Visual Pre-training | ✓ Link | 97.3 | Pixio-H + DPT | 2025-12-17 |
| The 3D Mirage: Probing and Taming 3D Hallucinations | 96.08 | Grounded Self-Distill | 2025-12-17 | |
| HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents | ✓ Link | 90.2 | HY-Embodied-0.5 MoE-A32B | 2026-04-08 |
| RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination | ✓ Link | 83.4 | RxBrain | 2026-07-15 |