ConClick: Element-Wise Contrastive Learning Improves GUI Grounding

arXiv:2610.13268 · cs.CV · Submitted 2026-10-09 · Read on arXiv

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 20 pages, 10 figures, including references and appendices. Code and data: https://github.com/zhangruotian/ConClick

Code: https://github.com/zhangruotian/ConClick

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Contrastive Learning — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-VL Technical Report
• V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking
• UI-Venus Technical Report: Building High-performance UI Agents with RFT
• Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding
• What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
• Decoupled Weight Decay Regularization
• UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
• FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• VISTA: View-Consistent Self-Verified Training for GUI Grounding
• UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
• GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
• Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
• BAMI: Training-Free Bias Mitigation in GUI Grounding

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models