AI Research Lab
GMD-AI
General Machine Intelligence for Discovery, Detection & Defense.
Discovery
We explore what AI makes possible.
Detection
When AI creates, we verify.
Defense
Where threats emerge, we stand guard.
0
Publications
0
Projects
0
Researchers
Recent activity
Latest papers, projects, and posts.
UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
Proceedings of the International Conference on Machine Learning (ICML) 2026
UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning
A resource-adaptive federated fine-tuning method that fixes the expert-imbalance and gradient-sparsity discordances of sparse MoE, achieving up to 45% computation reduction and 8.7x better low-resource performance over heterogeneous LoRA-rank methods.
AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection
International Joint Conference on Neural Networks (IJCNN) 2026
Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
Proceedings of the AAAI Conference on Artificial Intelligence 2026
TriDetect: Semi-supervised Generalized AI-generated Image Detection
A semi-supervised approach that discovers latent architectural patterns within fake images to achieve cross-generator generalization in deepfake detection.
Introducing GMD-AI: Why We Started This Group
The motivation behind GMD-AI and our three-pillar mission: Discovery, Detection, and Defense.