Research map / Vision-language and multimodal / Multimodal LLMs
EGM: Efficient Visual Grounding Language Models
Guanqi Zhan, Changye Li, Zhijian Liu, Yao Lu, Yi Wu, Song Han, Ligeng Zhu
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 EGM reasoning SFT+RL training | Qwen3-VL-2B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 83.6 -> 89.6 | Improved |
| add EGM reasoning SFT+RL training | Qwen3-VL-8B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 87.8 -> 91.4 | Improved |
| add EGM reasoning SFT+RL training | InternVL-3-1B · RefCOCO/+/g (8-split average) | accuracy: 81.6 -> 86.8 | Improved |
| add EGM reasoning SFT+RL training | InternVL-3-8B · RefCOCO/+/g (8-split average) | accuracy: 89.6 -> 90.7 | Improved |
| add the reasoning process to EGM (ablation) | InternVL-3-8B · RefCOCO/+/g (8-split average) | accuracy: 87.7 -> 90.7 | Improved |
| add the reasoning process to EGM (ablation) | Qwen3-VL-8B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 88.6 -> 91.4 | Improved |
| add the reasoning process to EGM (ablation) | Qwen3-VL-2B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 88.7 -> 89.6 | Improved |
| add the reasoning process to EGM (ablation) | InternVL-3-1B · RefCOCO/+/g (8-split average) | accuracy: 83.6 -> 86.8 | Improved |
| add RL stage after SFT (ablation) | Qwen3-VL-8B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 88.8 -> 91.4 | Improved |
| add SFT stage on reasoning data (ablation) | Qwen3-VL-4B-Thinking · RefCOCO/+/g (8-split average) | accuracy: 87.2 -> 87.9 | Improved |
| use Thinking instead of Instruct variant | Qwen3-VL 2B/4B/8B · RefCOCO/+/g (8-split average) | accuracy: -0.6/-0.1/-0.5 | No clear effect |
| add EGM amodal reasoning training | InternVL-3-8B · Amodal grounding (COCO-Amodal) | accuracy: 62.0 -> 73.5 | Improved |
Closest papers by meaning
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.92)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.92)
- Investigating Compositional Challenges in Vision-Language Models for Visual Grounding (CVPR 2024 · similarity 0.91)
- GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models (AAAI 2026 · similarity 0.90)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.90)
- GROUNDHOG: Grounding Large Language Models to Holistic Segmentation (CVPR 2024 · similarity 0.90)
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.
