Mohana Prasad Sathya Moorthy — accepted AI-conference papers

2025

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

Zhangheng LI, Keen You, Haotian Zhang, Di Feng, Harsh Agrawal, Xiujun Li +4

ICLR 2025poster

Building a generalist model for user interface (UI) understanding is challenging due to various foundational issues, such as platform diversity, resolution variation, and data limitation. In this paper, we introduce Ferret-UI 2, a multimodal large language model (MLLM) designed for universal UI unde…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents

Harsh Agrawal, Eldon Schoop, Xinlei Pan, Anuj Mahajan, Ari Seff, Di Feng +9

ICCV 2025poster

We build a comprehensive online evaluation benchmark for language-conditioned multi-step task execution on mobile interfaces. Our benchmark strives to evaluate the multi-step planning, reasoning, and visual grounding capabilities of agents, using mobile user interfaces as a concrete testbed. To buil…

Cited by 0 Source ↗PDF ↗Scholar ↗