Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Liang Ji

Liang Ji

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Networking×1Vision×1AI×1NLP×1Crypto×1ML×1

Frequent co-authors

Yaru Fu1×
Sabita Maharjan1×
Tony Q. S. Quek1×
Tom Maye-Lasserre1×
Yitong Li1×
Bailiang Jian1×

Research Timeline

2026
TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement

The paper proposes a novel adversarial defense approach, TopFeaRe, by modeling graph adversarial attacks using complex dynamic system theory to locate the graph's critical state of resilience.

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and diversity.

Token Communications (TokCom): A Unified AI-Native Communication Framework

This paper proposes a new communication framework, TokCom, for 6G wireless networks where tokens from large language models become the fundamental entities for information exchange.

Highlighted terms show continued research focus across papers

Papers

cs.NITheoreticalRecentJul 20, 2026

Token Communications (TokCom): A Unified AI-Native Communication Framework

Yaru Fu, Liang Ji, Sabita Maharjan, Tony Q. S. Quek

This paper proposes a new communication framework, TokCom, for 6G wireless networks where tokens from large language models become the fundamental entities for information exchange.

View →
cs.CVcs.AIcs.CLRecent
May 29, 2026

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation

Tom Maye-Lasserre, Yitong Li, Bailiang Jian, Morteza Ghahremani +2 more

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and d…

View →
cs.CRcs.LGRecentApr 15, 2026

TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement

Xinxin Fan, Wenxiong Chen, Quanliang Jing, Chi Lin +3 more

The paper proposes a novel adversarial defense approach, TopFeaRe, by modeling graph adversarial attacks using complex dynamic system theory to locate the graph's critical state of resilience.

View →