Research map / Detection and segmentation / Open-set and few-shot detection
Detect Anything via Next Point Prediction
Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, Zhaoyang Zeng, Yihao Chen, Tianhe Ren, Junzhi Yu, Lei Zhang
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 |
|---|---|---|---|
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · COCO | F1@IoU0.5: 68.2 -> 72.0 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · LVIS | F1@IoU0.5: 60.3 -> 64.3 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · Dense200 | F1@IoU0.5: 60.2 -> 78.4 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · VisDrone | F1@IoU0.5: 55.6 -> 61.6 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · HumanRef | F1@IoU0.5: 83.3 -> 85.4 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · RefCOCOg val | F1@IoU0.5: 84.9 -> 86.6 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · Dense200 pointing | F1@Point: 72.9 -> 82.5 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · VisDrone pointing | F1@Point: 49.5 -> 58.9 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · ScreenSpot-Pro | accuracy avg: 32.6 -> 36.8 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · ScreenSpot-V2 | accuracy avg: 86.4 -> 88.4 | Improved |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · LVIS | F1@IoU0.95: 20.7 -> 20.7 | No clear effect |
| add GRPO post-training with geometry-aware rewards after SFT (ablation) | Rex-Omni · Dense200 | F1@IoU0.95: 10.6 -> 10.3 | No clear effect |
Closest papers by meaning
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.88)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- Aligning and Prompting Everything All at Once for Universal Visual Perception (CVPR 2024 · similarity 0.87)
- ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models (CVPR 2025 · similarity 0.87)
- UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling (NeurIPS 2024 · similarity 0.87)
- Interpreting Object-level Foundation Models via Visual Precision Search (CVPR 2025 · similarity 0.87)
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.
