activity
20242026
collaborators

7 papers

cs.AI2026

Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination

Runzhe Liu, Biquan Bie, Zihao Wang +7

The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic patterns rather than reproduce…

cs.AI2026

Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure

Guijia Zhang, Harry Yang, Yuxun Chen +1

Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and a serialized structure such as a document object model or accessibil…

cs.AI2026

Hallucination as Exploit: Evidence-Carrying Multimodal Agents

Guijia Zhang, Hao Zheng, Harry Yang

Multimodal agents increasingly choose tool calls from screenshots, documents, and webpages, where a false perceptual claim can turn hallucination from an answer-quality error into…

cs.LG2025

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments

Yipeng Du, Zihao Wang, Ahmad Farhan +7

The deployment of large-scale models, such as large language models (LLMs), incurs substantial costs due to their computational demands. To mitigate these costs and address challen…

cs.CR2025

Encrypted Large Model Inference: The Equivariant Encryption Paradigm

James Buban, Hongyang Zhang, Claudio Angione +10

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer v…

cs.CR2024

Towards Secure and Private AI: A Framework for Decentralized Inference

Hongyang Zhang, Yue Zhao, Claudio Angione +5

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable ou…