collaborators

10 papers

cs.LG2025

Structural Disentanglement of Causal and Correlated Concepts

Qilong Zhao, Shiyu Wang, Zeeshan Memon +5

Controllable data generation aims to synthesize data by specifying values for target concepts. Achieving this reliably requires modeling the underlying generative factors and their…

stat.ML2025

Continuous Domain Generalization

Zekun Cai, Yiheng Yao, Guangji Bai +4

Real-world data distributions often shift continuously across multiple latent factors such as time, geography, and socioeconomic contexts. However, existing domain generalization a…

cs.CV2025

Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation

Mengdan Zhu, Senhao Cheng, Guangji Bai +2

Text-to-image generation increasingly demands access to domain-specific, fine-grained, and rapidly evolving knowledge that pretrained models cannot fully capture, necessitating the…

cs.LG2025

StructPrune: Structured Global Pruning asymptotics with GPU Memory

Xinyuan Song, Guangji Bai, Liang Zhao

Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires memory, which is infeasible for billion-param…

cs.CV2025

Saliency-Bench: A Comprehensive Benchmark for Evaluating Visual Explanations

Yifei Zhang, James Song, Siyi Gu +4

Explainable AI (XAI) has gained significant attention for providing insights into the decision-making processes of deep learning models, particularly for image classification tasks…

cs.LG2025

FedSpaLLM: Federated Pruning of Large Language Models

Guangji Bai, Yijiang Li, Zilinghan Li +2

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. Pruning can reduce model size,…