Publications (6)
EMK-KEN: A High-Performance Approach for Assessing Knowledge Value in Citation Network
Zehui Qu, Chengzhi Liu, Hanwen Cui +1
With the explosive growth of academic literature, effectively evaluating the knowledge value of literature has become quite essential. However, most of the existing methods focus o…
Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners
Zheng Lu, Mingqi Gao, Qinlei Xie +8
Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning. This rewards models that mimic…
A Survey on Agent Workflow -- Status and Future
Chaojia Yu, Zihan Cheng, Hanwen Cui +5
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memor…
Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
Xunkai Li, Zhengyu Wu, Jiayi Wu +4
With the increasing prevalence of cross-domain Text-Attributed Graph (TAG) Data (e.g., citation networks, recommendation systems, social networks, and ai4science), the integration…
Significantly Enhanced Vacancy Diffusion in Mn-containing Alloys
Huaqing Guan, Hanwen Cui, Ning Ding +12
Manipulating point defects for tailored macroscopic properties remains a formidable challenge in materials science. This study demonstrates a proof-of-principle for a universal law…
StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment
Hanwen Cui, Yuting Mei, Yuhang Fu +2
Story rewriting aims to adapt existing narratives to diverse reader preferences while preserving plot consistency and narrative coherence. Unlike conventional work on style transfe…