Research map / Vision-language and multimodal / Human and embodied modeling
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
A. Said Gurbuz, Sunghwan Hong, Ahmed Nassar, Marc Pollefeys, Peter W. J. Staar
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 structure-aware weighted loss (upweight tag and location tokens) (ablation) | ScreenVLM · ScreenParse test | Page IoU: 0.592 -> 0.606 | Improved |
| add structure-aware weighted loss (ablation) | ScreenVLM · ScreenSpot PC | Recall@50: 0.129 -> 0.222 | Improved |
| add structure-aware weighted loss (ablation) | ScreenVLM · GroundCUA | Page IoU: 0.226 -> 0.251 | Improved |
| fine-tune on ScreenParse | Qwen3-VL-2B-Instruct · ScreenParse test | Page IoU: 0.228 -> 0.585 | Improved |
| fine-tune on ScreenParse | InternVL3-2B · ScreenParse test | Page IoU: 0.111 -> 0.509 | Improved |
| fine-tune on ScreenParse | InternVL3-2B · GroundCUA | Page IoU: 0.025 -> 0.203 | Improved |
| fine-tune on ScreenParse | Qwen3-VL-2B-Instruct · ScreenSpot Mobile | Recall@50: 0.143 -> 0.108 | Hurt |
| fine-tune on ScreenParse | Qwen3-VL-2B-Instruct · ScreenSpot Web | PixCov: 0.292 -> 0.720 | Improved |
| fine-tune OmniParser V2 on ScreenParse | OmniParser V2 · ScreenParse test | Page IoU: 0.270 -> 0.503 | Improved |
| fine-tune OmniParser V2 on ScreenParse | OmniParser V2 · GroundCUA | Page IoU: 0.361 -> 0.398 | Improved |
| swap OmniParser v2 detector for ScreenParse-trained YOLO | Set-of-Mark pipeline · Mind2Web (task) | step success: 26.8 -> 27.0 | No clear effect |
| swap OmniParser v2 detector for ScreenParse-trained YOLO | Set-of-Mark pipeline · OSWorld-G fine-grained manipulation | accuracy: 25.50 -> 29.53 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- OmniParser V2 — OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models (TPAMI 2026) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis (NeurIPS 2025 · similarity 0.88)
- FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection (CVPR 2026 · similarity 0.87)
- GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding (ICML 2026 · similarity 0.85)
- GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents (NeurIPS 2025 · similarity 0.85)
- Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents (ICLR 2025 · similarity 0.85)
- Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels (CVPR 2025 · similarity 0.84)
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.
