Qinchuan Cheng

Xi'an Jiaotong University, Xi'an

Undergraduate
Egocentric Compilation
LLM Post-Training & Agents
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
  • Experience
  • Contact
中文

Publications

Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
October 2026 Under review
#Egocentric Compilation #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
EgoVine: Post-Training with Branching Experience Compiled from Real-World Videos
September 2026 Under review
#Egocentric Compilation #LLM Post-Training #Embodied AI

A post-training framework that restores decision states, executes alternative branches, and verifies continuations to construct interactive experience for embodied planners.

View
TransRheo: A Physics-Informed Multi-Task Numeric Transformer for Polymer Nanocomposite Rheology
March 2026 Interdisciplinary Materials (under review)
#AI for Science #Materials #Transformer #Scientific ML

A physics-informed numeric Transformer for polymer nanocomposite rheology prediction with natural-language knowledge encoding and monotonicity constraints.

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 (second-round 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.

HotShardGNN: Migration-Budgeted Hotspot Repartitioning for Distributed Temporal Graph Neural Network Training
Qinao Hu†*, Qinchuan Cheng†, Dadi Liu, Junhan Xu ICPADS
#Graph Neural Networks #Distributed Training

Migration-budgeted hotspot repartitioning for distributed temporal graph neural network training.

© 2026 Qinchuan Cheng.
蜀ICP备2026009169号