Qinchuan Cheng

Xi'an Jiaotong University, Xi'an

Undergraduate researcher
Research focus
Multimodal foundation models
LLM agents and AI for Science
Avatar of Qinchuan Cheng
Email
QQ 2310820636@qq.com Institution cdzqzwd20041108@stu.xjtu.edu.cn
GitHub Scholar ORCID iD 中文
  • About
  • Publications
  • Projects
  • Experience
  • Contact
中文

Publications

Papers, submissions, and research outputs.

Ego2World: Video-Compiled Symbolic Simulation for Embodied Agent Evaluation
May 2026 Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Xulei Yang, Shijie Li Submitted to NeurIPS 2026
#Multimodal Models #Embodied AI #LLM Agent #Benchmark

A symbolic simulation environment compiled from real kitchen videos for evaluating large-model agents on long-horizon embodied tasks.

View
MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation
May 2026 Qinchuan Cheng, Ruixuan Xie, Jiaqi Liu, Xiaoya Yuan, Yuxin Liu Technical preprint in preparation
#Legal AI #LLM Agent #RAG #Retrieval Control

A retrieval-control framework for legal consultation based on element coverage, evidence coverage, and marginal gain.

View
TransRheo: A Physics-Informed Multi-Task Numeric Transformer for Polymer Nanocomposite Rheology
March 2026 Bily Cheng, collaborators Preparing for submission
#AI for Science #Materials #Transformer #Scientific ML

A physics-informed numeric transformer for rheology prediction in polymer nanocomposites, with scientific-ML and agent-workflow integration.

Optimal EV Charging Station Location through a Dominant-Strategy Incentive-Compatible and LLM-Assisted Multilevel Auction
January 2026 Donghe Li, Qinchuan Cheng, Wenzhuo Li, Xiao Liao, Junhan Xu, Meng Zhao, Huan Xi, Qingyu Yang Applied Energy (revision)
#LLM #Mechanism Design #Optimization #Energy Systems

A multilevel-auction and LLM-assisted planning framework for EV charging-station location under preference uncertainty and incentive constraints.

© 2026 Qinchuan Cheng.
蜀ICP备2026009169号