已审阅并标注「界面理解」的研究与资产。
条目依据已审阅标签归类，同一主题不表示资源之间存在依赖关系。日期保留来源精度，注释保留原语言。
ScreenParse supplies dense annotations of UI elements, types and text in web screenshots through an automated rendering and filtering pipeline. ScreenVLM learns to output structured screen markup, and the study evaluates dense parsing and transfer to GUI grounding.
GUI-GenBench tests image-generation models as action-conditioned GUI environments across five suites, including transitions, trajectories and grounding. Its VLM-based GUI-Score separates goal completion, interaction logic, consistency and visual properties.
An anonymization framework replaces sensitive screen content and instructions with consistent, type-preserving placeholders while mediating actions through a local interaction proxy. Experiments on AndroidLab and PrivScreen examine the privacy–utility trade-off when mobile GUI agents operate over these transformed interfaces.
Trifuse combines attention-based localization with OCR text cues and icon captions to ground GUI instructions. Its fusion procedure favors cross-modal agreement and sharp location peaks, and is evaluated without task-specific fine-tuning.
gWorld predicts future mobile GUI states as renderable web code and supplies an automated pipeline for code-based training data. The study evaluates visual state prediction and how stronger world models affect downstream mobile policies.
GUI-Eyes trains GUI grounders to decide when and how to use visual tools such as crops and zooms. Its coarse-to-fine policy uses dense spatial rewards based on location proximity and region overlap, with evaluation on ScreenSpot-Pro.
FocusUI selects instruction-relevant screenshot patches while preserving their positional structure for GUI grounding. Its PosPad scheme replaces runs of dropped tokens with positional markers and is evaluated under reduced token budgets.
Introduces iSHIFT, which combines latent reasoning with perception-control tokens to adapt GUI inference. The agent switches between detailed regional grounding and faster use of global visual cues.
DAVE trains a vision encoder for document images and web agents using self-supervised pretraining followed by supervised parsing and localization. It combines decoder-specific encoder merging with feature fusion and evaluates web localization and agent benchmarks alongside document tasks.
ZoomClick uses repeated zooming and context adjustment to improve GUI grounding without training. The paper studies zoom depth, crop sizes, and related choices and introduces GUIZoom-Bench to evaluate how grounding models respond to zoomed views.
MPR-GUI evaluates GUI perception and reasoning through strictly aligned tasks in six languages. GUI-XLI adjusts non-English hidden representations toward English representations at language-sensitive layers during inference to address the measured cross-language gaps.
Introduces Prune4Web, where generated scoring programs filter DOM elements according to decomposed subtasks before grounding. An annotation pipeline and two-turn training procedure coordinate the planner, programmatic filter and grounder.
Introduces MEGA-GUI, which separates coarse region selection from fine-grained interface-element grounding. Bidirectional zooming and context-aware instruction rewriting coordinate specialized vision-language agents across visual scales.
Introduces GUI-AIMA, which supervises instruction-relevant attention over visual patches instead of directly training coordinate text generation. Patch-level grounding can be combined with an optional zoom stage and is evaluated across GUI localization benchmarks.
GUIrilla systematically explores macOS interfaces to collect interaction traces and accessibility metadata for downstream GUI research. It organizes these observations into hierarchical MacApp Trees and describes an accessibility-driven collection library.
This work addresses GUI localization errors caused by mismatches between visual patch positions and output pixel coordinates. RULER tokens provide explicit coordinate references, while Interleaved MRoPE balances width and height encoding; evaluation uses the ScreenSpot benchmark family.
GUI-KV compresses vision-language agents’ attention caches using visual-token saliency and redundancy between screenshot frames. The method requires no retraining and evaluates how cache budgets affect GUI action accuracy and computational cost.
GUI-PRA evaluates GUI progress by generating task-specific criteria and actively inspecting visual evidence with tools. It tests offline judgment on OS-Critic Bench and the effects of this feedback on online mobile policies in AndroidWorld.
Evaluates multimodal LLMs on web interface reasoning, visual perturbation robustness, and safety-critical web understanding tasks.
GUI-ARP uses visual attention to crop relevant screenshot regions and decides whether a target needs single-stage or multi-stage analysis. Supervised fine-tuning followed by GRPO trains this adaptive procedure for high-resolution GUI grounding.
Studies the gap between latent visual grounding and explicit coordinate output in general vision-language models. Three zero-shot methods add axes, grids, or labeled intersections to GUI screenshots so models can express spatial locations without fine-tuning.
Introduces SparkUI-Parser, which adds continuous coordinate decoding and a rejection mechanism for nonexistent targets to a multimodal model. It also presents ScreenParse for evaluating structural interface perception.
LASER builds preference data for multi-step GUI perception by combining Monte Carlo quality estimates with region-overlap evaluation. Its self-evolving training encourages relevant region selection and adapts the amount of reasoning before predicting screen coordinates.
V2P trains GUI grounding by suppressing attention to background regions and emphasizing the center of the target element. It represents target importance with size-dependent Gaussian heatmaps and evaluates the contribution of each component on ScreenSpot-v2 and ScreenSpot-Pro.
FineState-Bench evaluates fine-grained GUI perception and control across desktop, web, and mobile interfaces. Its Visual Diagnostic Assistant separates perception and localization contributions in controlled interaction experiments.
D2Snap reduces serialized DOM observations while preserving actionable elements and features that distinguish their uses. The study compares reduced DOM inputs with screenshot-based observations for a web agent on tasks sampled from Online-Mind2Web.
RecAgent narrows attention to recommended UI components and requests user feedback when task intent or decisions remain uncertain. It introduces ComplexAction to evaluate specified single-step GUI actions in difficult interface scenarios.
Reports a GUI-grounding model family and empirical design choices covering source data, perception training, and coordinate prediction.
R-VLM localizes GUI elements through zoomed-in region proposals and an intersection-over-union-aware training objective. It evaluates the grounding model on ScreenSpot and AgentStudio and studies its effect on navigation in AITW and Mind2Web.
Separates textual and iconic UI elements and iteratively focuses visual regions to refine grounding without additional model training.
Open CaptchaWorld evaluates multimodal agents on interactive browser-based CAPTCHA puzzles. Its benchmark distinguishes task success from the depth of visual reasoning and interaction needed to complete a puzzle.
Introduces WiserUI-Bench, pairing real UI variants from industry A/B tests with observed behavioral winners and expert explanations. It evaluates models’ ability to predict the more effective interface and explain its effect on user behavior.
RegionFocus adds visual test-time scaling by zooming into selected screenshot regions and maintaining an image-based map of landmarks and actions. It evaluates this grounding procedure with UI-TARS and Qwen2.5-VL on ScreenSpot-Pro and WebVoyager.
Introduces PixelWeb, a webpage GUI dataset with element images, contours, and pixel masks. Its annotation pipeline combines bitmap channel information with DOM-based visibility and stacking analysis to address occlusion and overlapping elements.
Represents interface interactions with a stateful screen schema to model user behavior and support action understanding and prediction.
Provides annotated desktop demonstrations for evaluating element grounding, layout grounding, and action prediction.
Uses specialized graphical, textual, and spatial perception components with a data-collection pipeline to improve GUI understanding.
Introduces AutoCaptioner, DeskVision, and GUIExplorer for generating desktop region descriptions and training interface-understanding models.
Introduces SpiritSight and GUI-Lasagne data, combining multilevel GUI annotations with visual block parsing for high-resolution interface navigation.
Combines hierarchical screen parsing with spatially enriched element descriptions to support both locating GUI targets and describing indicated elements.
Combines information-sensitive image cropping with a learning loop between element description and grounding for complex interface understanding.
Pretrains GUI-context understanding with instruction-free web interactions before fine-tuning Falcon-UI on instructed GUI tasks.
Synthesizes GUI training examples at multiple levels of detail from webpages and studies transfer of learned understanding to other interface environments.
Extends Ferret-UI across device platforms with adaptive visual scaling and synthetic data for referring, grounding, and user-centered UI tasks.
Builds MultiUI by generating instructions from webpage accessibility trees and pairing them with screenshots for multimodal training. Evaluation examines web-interface understanding, including VisualWebBench and Mind2Web, and transfer to other text-rich visual tasks.
Generates labeled slides and interface visuals through code to support visual element detection, description, and classification with less manual annotation.
Introduces IconDesc, which generates mobile icon alt-text from partial UI context such as element identifiers, bounds, nearby text and hierarchy. Model evaluation and a user study examine the resulting accessibility descriptions.
MobileVLM adds two pretraining stages and four UI tasks to learn element detail and relationships between successive screens. Its Mobile3M dataset contains three million Chinese mobile UI pages connected by recorded transition actions.
Builds mobile screenshot and view-hierarchy pairs through automated application traversal and evaluates their usefulness for GUI grounding.
Studies how the ordering of UI elements in an agent observation affects web and desktop performance. A pixel-based element detector and dimensionality-reduction ordering are evaluated on OmniACT when document hierarchy is unavailable.
Orienter detects interactable GUI elements in XR applications by interpreting scene context and revisiting candidate elements through a validation and reflection loop. It addresses open-vocabulary element types and context-dependent interactability.
PeriGuru interprets smartphone GUI screenshots with computer vision and uses a language model to decide the next action. A peripheral robotic arm executes the phone interactions, providing an alternative mechanism for operating mobile apps.
Introduces question answering over individual screens, multiple web pages, and navigation traces to test information synthesis across views.
Parses screenshots into interactable regions and semantic element descriptions to support visually grounded agent actions.
Introduces designer-authored mobile UI critiques and quality ratings, studying how targeted examples improve automated design feedback.
Introduces a mobile GUI model using hybrid visual encoders, mixture-of-experts expansion, and alignment training for multilingual interfaces.
Introduces Android screenshots with element locations, functionality descriptions, and instructions linked to sequences of GUI actions.
Trident combines exploration, monitoring, and detection agents to identify functional bugs that do not crash a mobile app. It reasons over screenshot sequences and interface transitions to construct test oracles, evaluated on 590 non-crash bugs and additional live apps.
Introduces Screen Point-and-Read and a hierarchical layout approach that interprets screen regions indicated by a user-selected point.
Defines goal identification from observed UI trajectories and an evaluation method for comparing intent descriptions within the same interface context. Experiments reuse Android and web automation data to compare human and model inference of users’ detailed goals.
第 61–120 条，共 212 条资源。
通过主题导出清单获取完整记录和证据。克隆目录后，可将主题记录直接交给标准 RAG 与引用导出工具。
