7 papers
TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
Suizhi Huang, Mei Li, Han Yu +1
Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause o…
Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment
Hongyi Peng, Han Yu, Xiaoxiao Li +1
Low-Rank Adaptation (LoRA) is widely used for federated fine-tuning. Yet under non-IID settings, it can substantially underperform full-parameter fine-tuning. Through with-high-pro…
Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation
Anran Li, Yuanyuan Chen, Wenjun Long +16
Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because privacy and governance constraints…
Class-wise Balancing Data Replay for Federated Class-Incremental Learning
Zhuang Qi, Ying-Peng Tang, Lei Meng +3
Federated Class Incremental Learning (FCIL) aims to collaboratively process continuously increasing incoming tasks across multiple clients. Among various approaches, data replay ha…
Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
Zhuang Qi, Pan Yu, Lei Meng +4
Federated Prompt Learning (FPL) enables communication-efficient adaptation by tuning lightweight prompts on top of frozen pre-trained models. Existing FPL methods typically rely on…
PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis
Beidi Zhao, SangMook Kim, Hao Chen +4
Multiple Instance Learning (MIL) has advanced WSI analysis but struggles with the complexity and heterogeneity of WSIs. Existing MIL methods face challenges in aggregating diverse…