Yifei Zhang

Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification

RoBlock: Wide and Deep Scaling of Recommenders via Embedding Collapse Mitigation

Towards Interference-Free One-Shot Federated Learning via Frequency Domain Aggregation

Provably Continual Unlearning for Large Language Model

Orthogonal Updates Are Optimal for Continual Learning

CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Machine Unlearning via Task Simplex Arithmetic

Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs

PISA: Compressive Sensing Adaptation of Large Language Models

Parrot: Seamless Spoken Dialogue Interaction with Double-Channel Large Language Models