Xing Tang

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

CORE: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning

WingsFL: Speed-up Federated Learning via Co-optimization of Communication Frequency and Gradient Compression Ratio

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation

Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency

Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning