Xiaoxiao Li

Textual Equilibrium Propagation for Deep Compound AI Systems

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning

Cross-View Lewis Weight Fusion Empowering Exemplar Replay for Federated Class-Incremental Learning

Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following

Efficient Forward-Only Data Valuation For LLMs and VLMs

Information Bottleneck-inspired Efficient and Explainable Federated Active Learning

Class-wise Balancing Data Replay for Federated Class-Incremental Learning

A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning

Multi-Session Budget Optimization for Forward Auction-based Federated Learning

GMValuator: Similarity-based Data Valuation for Generative Models

On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

Can Textual Gradient Work in Federated Learning?

S4M: S4 for multivariate time series forecasting with Missing values

Commute Graph Neural Networks

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

Multi-Session Budget Optimization for Forward Auction-based Federated Learning

Semantic-aligned Query Synthesis for Active Learning