5 papers
TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity
Chengwei Shi, Yunnong Chen, Tingting Zhou +5
A key challenge for multimodal large language models (MLLMs) is moving beyond visual recognition to constraint-aware cross-modal reasoning. This involves combining visual cues with…
On Reasoning-Centric LLM-based Automated Theorem Proving
Yican Sun, Chengwei Shi, Hangzhou Lyu +1
Automated theorem proving is fundamental to formal methods, and the recent trend is to integrate large language models (LLMs) and proof assistants to form effective proof agents. W…
SpecifyUI: Supporting Iterative UI Design Intent Expression through Structured Specifications and Generative AI
Yunnong Chen, Chengwei Shi, Liuqing Chen
Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We…
StyGazeTalk: Learning Stylized Generation of Gaze and Head Dynamics
Chengwei Shi, Chong Cao
Gaze and head movements play a central role in expressive 3D media, human-agent interaction, and immersive communication. Existing works often model facial components in isolation…
Using Large Language Models to Generate Clinical Trial Tables and Figures
Yumeng Yang, Peter Krusche, Kristyn Pantoja +4
Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered r…