Research

We form small and agile teams around high-impact research problems. Each project pairs academic rigor with strong engineering to deliver both publications and practical artifacts (code, datasets, demos).

Areas

Publications

figure
A Comprehensive Review of Deep Learning in EEG-based Emotion Recognition: Classifications, Trends, and Practical Implications
PeerJ Computer Science
W Ma, Y Zheng, T Li, Z Li, Y Li, L Wang
EEGPattern Recognition
publication
figure
A Survey of Context Engineering for Large Language Models
Under Review
L Mei, J Yao, Y Ge, Y Wang, B Bi, Y Cai, J Liu, M Li, Z Li, D Zhang, C Zhou, J Mao, T Xia, J Guo, S Liu
LLM
preprint
figure
A1: Steep Sest-time Scaling Law Via Environment Augmented Generation
Under Review
L Mei, S Liu, Y Wang, B Bi, Y Ge, J Wan, Y Wu, X Cheng
LLM
preprint
figure
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
MLCommons Technical Report
S Ghosh, H Frase, A Williams, S Luger, P Röttger, F Barez, S McGregor, K Fricklas, ... (101 in total)
LLMSecurity
preprint · website · code
figure
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Under Review
Y Zheng, T Li, H Huang, T Zeng, J Lu, C Chu, Y Huang, Z Jiang, Q Xiong, Y Ge, M Li
LLMSecurity
preprint · code
figure
Attack Based on Data: A Novel Perspective to Attack Sensitive Points Directly
Cybersecurity
Y Ge, Z Yang, L Chen, Y Wang, C Li
Security
publication
figure
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
EMNLP 2025 Findings
Q Xiong, Y Huang, Z Jiang, Z Chang, Y Zheng, T Li, M Li
LLM AgentSecurity
preprint · code
figure
Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
ACL 2025
Y Ge, S Liu, W Feng, L Mei, L Chen, X Cheng
LLM
preprint · code
figure
DSRP: A Database for Stress Reduction Using Physiological Signals
IEEE Access
Z Li, W Ma, J Zhang, Y Li, L Wang, Y Hao, X Li
EEGPattern Recognition
publication
figure
From Droplets to Diagnosis: AI-Driven Imaging and System Integration in Digital Nucleic Acid Amplification Testing
Biosensors and Bioelectronics
Y Wei, X Liu, Y Mu, C Xu, G Zhang, T Li, Z Li, W Yuan, HP Ho, M Xu
Digital Medicine
publication
figure
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Under Review
Y Ge, S Liu, Y Wang, L Mei, L Chen, B Bi, X Cheng
LLM
preprint
figure
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
ACL 2025 (SAC Highlights)
Z Jiang, M Li, G Yang, J Wang, Y Huang, Z Chang, Q Wang
LLM AgentSecurity
preprint · code
figure
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
Under Review
Z Chang, M Li, X Jia, J Wang, Y Huang, Z Jiang, Y Liu, Q Wang
LLMSecurity
preprint · code
figure
PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression
Under Review
L Chen, B Zhou, Y Ge, J Chen, S Ni
LLM
preprint · code
figure
SFSWTS: A Spatial-Frequency Shifted Windows and Time Self-Attention Network for EEG Emotion Recognition
Neurocomputing
W Ma, Y Li, T Li, H Yang, Z Li, L Wang, J Xuan
EEGPattern Recognition
publication
figure
SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
AAAI-25 Workshop on Artificial Intelligence for Cyber Security (AICS) 20-min Oral
T Li, J Lu, C Chu, T Zeng, Y Zheng, M Li, H Huang, B Wu, Z Liu, K Ma, X Yuan, X Wang, K Ding, H Chen, Q Zhang
LLMSecurity
preprint · code · data
figure
Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation
ICLR 2025 SynthData
T Li, T Zeng, Y Zheng, C Zhang, J Lu, H Huang, C Chu, FF Yin, Z Yang
Medical ImageSecurity
preprint · website
figure
Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
Under Review
J Yao, S Liu, Y Wang, L Mei, B Bi, Y Ge, Z Li, X Cheng
LLM
preprint

For collaboration or to share your preprint with us, please get in touch.