3 papers
cs.SE2026
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…
cs.GR2026
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…
cs.HC2025
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…