@HuggingPapers: Microsoft just released Phi-Ground-Any on Hugging Face A 4B parameter vision model for GUI grounding that achieves SOTA…
Summary
Microsoft has released Phi-Ground-Any, a 4B parameter vision model for GUI grounding on Hugging Face that achieves state-of-the-art results, enabling AI agents to precisely interact with screen elements.
View Cached Full Text
Cached at: 05/09/26, 02:10 PM
Microsoft just released Phi-Ground-Any on Hugging Face
A 4B parameter vision model for GUI grounding that achieves SOTA results on
ScreenSpot-pro and UI-Vision, enabling AI agents to precisely click screen elements. https://t.co/VAgTlRPUbB
Similar Articles
GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning
提出 ScreenRef 高质量 GUI grounding 数据集（586K 截图、633K 指代表达实例）和 Distillation-to-Reinforcement Learning（D2RL）训练方法，训练出 GroundGUI-8B，在 ScreenSpot-V2 等多个基准上取得 8B 级模型中的领先性能。
@HuggingPapers: Microsoft just released Lens on Hugging Face A 3.8B parameter text-to-image model delivering efficient training and hig…
Microsoft released Lens, a 3.8B parameter text-to-image model on Hugging Face, capable of efficient training and high-resolution generation up to 1440×1440.
@HuggingPapers: PhysBrain 1.5: Open-source SOTA for Embodied AI A single 8B model that understands scenes, generates robot actions, and…
PhysBrain 1.5 is an open-source 8B parameter model for embodied AI that achieves state-of-the-art performance by understanding scenes, generating robot actions, and predicting future frames, scoring 72.5 on 28 benchmarks.
DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
DRS-GUI proposes a training-free dynamic region search framework for GUI grounding, using a lightweight UI Perceptor with human-like perceptual actions and Monte Carlo Tree Search to progressively locate instruction-relevant elements. Experiments show a 14% improvement on ScreenSpot-Pro for both general and GUI-specific MLLMs.
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
GroundingPI：一个 4B 参数的视觉定位基础模型，以量化坐标生成点与框，在 34 个定位基准上以 73.68% 平均成绩超越 GPT-6 Astra 等 44 个基线，并在机器人操作与自动驾驶下游任务中显著提升性能。