Tianci Liu

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Automatic Task-aware Instruction Optimizer for Black-box LLMs

Neat: Nonlinear Parameter-efficient Adaptation of Pre-trained Models

Counterfactual Fairness by Combining Factual and Counterfactual Predictions

Towards Poisoning Fair Representations

FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

One Training Fits All: Addressing Model-Heterogeneity Federated Learning via Architecture Probing