chenglin cai — accepted AI-conference papers

2026

UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as Reasoning

Liangyu Chen, Hanzhang Zhou, chenglin cai, Jianan Zhang, Panrong Tong, Xu Zhang +7

ICLR 2026poster

GUI grounding, which maps natural-language instructions to actionable UI elements, is a core capability of GUI agents. Prior work largely treats instructions as a static proxy for user intent, overlooking the impact of instruction diversity on grounding performance. Through a careful investigation o…

Cited by 0 Source ↗code ↗Scholar ↗

2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du, Yifan Yao, Kaijing Ma, Bingli Wang, Tianyu Zheng, King Zhu +89

NeurIPS 2025poster

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs…

Cited by 215 Source ↗Scholar ↗