7 papers
MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning
Mengchen Fan, Qizhen Lan, Xi Xiao +6
Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but r…
BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
Qizhen Lan, Mengchen Fan, Hang Zhang +5
Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings within vol…
CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning
Baraa Bilbeisi, Mengchen Fan, Baocheng Geng +1
Conventional federated learning (FL) relies on parameter averaging, which forces clients to be doubly homogeneous: it demands an identical architecture and degrades under non-IID d…
Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
Mengchen Fan, Baocheng Geng, Xi Xiao +5
Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefore necessary, but compact 3D…
Full-Frequency Temporal Patching and Structured Masking for Enhanced Audio Classification
Aditya Makineni, Baocheng Geng, Qing Tian
Transformers and State-Space Models (SSMs) have advanced audio classification by modeling spectrograms as sequences of patches. However, existing models such as the Audio Spectrogr…
PFedDST: Personalized Federated Learning with Decentralized Selection Training
Mengchen Fan, Keren Li, Tianyun Zhang +2
Distributed Learning (DL) enables the training of machine learning models across multiple devices, yet it faces challenges like non-IID data distributions and device capability dis…
Measuring Heterogeneity in Machine Learning with Distributed Energy Distance
Mengchen Fan, Baocheng Geng, Roman Shterenberg +3
In distributed and federated learning, heterogeneity across data sources remains a major obstacle to effective model aggregation and convergence. We focus on feature heterogeneity…