Imagen de Portada

What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Jiaping, Shen, Fei, Li, Junzhe, Nie, Ping, Yu, Fei, Li, Ming, Li, Haizhou
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs
por: Li, Weiming, et al.
Publicado: (2025)

TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
por: Guo, Chaohong, et al.
Publicado: (2025)

AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs
por: Li, Hongxin, et al.
Publicado: (2025)

Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
por: Guo, Hao, et al.
Publicado: (2026)

POINTS-GUI-G: GUI-Grounding Journey
por: Zhao, Zhongyin, et al.
Publicado: (2026)

GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
por: Li, Junlong, et al.
Publicado: (2026)

Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
por: Zong, Yongshuo, et al.
Publicado: (2025)

ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
por: Wang, Xiaoce, et al.
Publicado: (2026)

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency
por: Du, Yong, et al.
Publicado: (2025)

Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks
por: Li, Chenjun
Publicado: (2026)

GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction
por: Li, Hongxin, et al.
Publicado: (2026)

GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding
por: Tang, Fei, et al.
Publicado: (2025)

What Happens Next? Next Scene Prediction with a Unified Video Model
por: Li, Xinjie, et al.
Publicado: (2025)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
por: Kolli, Govinda, et al.
Publicado: (2026)

VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks
por: Zhou, Beitong, et al.
Publicado: (2025)

Motion Modes: What Could Happen Next?
por: Pandey, Karran, et al.
Publicado: (2024)

MVP: Multiple View Prediction Improves GUI Grounding
por: Zhang, Yunzhu, et al.
Publicado: (2025)

Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models
por: Yang, Fan, et al.
Publicado: (2025)

UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
por: Tang, Fei, et al.
Publicado: (2026)

Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
por: Li, Aiden Yiliu, et al.
Publicado: (2025)

GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents
por: Ye, Xianhang, et al.
Publicado: (2025)

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
por: Nie, Sen, et al.
Publicado: (2026)

Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
por: Tang, Fei, et al.
Publicado: (2025)

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning
por: He, Jixuan, et al.
Publicado: (2026)

AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement
por: Pei, Siqi, et al.
Publicado: (2026)

Geometry-Grounded Gaussian Splatting
por: Zhang, Baowen, et al.
Publicado: (2026)

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
por: Zhang, Yan, et al.
Publicado: (2026)

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
por: Wu, Qianhui, et al.
Publicado: (2025)

T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding
por: Guo, Chaohong, et al.
Publicado: (2026)

Perceptual Inductive Bias Is What You Need Before Contrastive Learning
por: Li, Tianqin, et al.
Publicado: (2025)

GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration
por: Fan, Yue, et al.
Publicado: (2025)

Continuous Speculative Decoding for Autoregressive Image Generation
por: Wang, Zili, et al.
Publicado: (2024)

Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
por: Chang, Chun-Peng, et al.
Publicado: (2026)

On the Robustness of GUI Grounding Models Against Image Attacks
por: Zhao, Haoren, et al.
Publicado: (2025)

Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning
por: Xu, Hai-Ming, et al.
Publicado: (2024)

\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
por: Lei, Bin, et al.
Publicado: (2025)

VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement
por: Du, Jun, et al.
Publicado: (2025)

AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark
por: Li, Hongxin, et al.
Publicado: (2026)

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
por: Ge, Zhiqi, et al.
Publicado: (2024)

Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles
por: Liao, Haicheng, et al.
Publicado: (2025)