Zhan Zhuang

MoSA: Mosaic Shared Adaptation of Large Language Models

Rethinking the Flow-based Gradual Domain Adaption: A Semi-Dual Transport Perspective

One-Token Verification for Reasoning LLMs, Anytime, Anywhere

Heterogeneous Incremental Learning for Dense Prediction: Advancing Knowledge Retention via Self-Distillation

HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models

MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition

MTSAM: Multi-Task Fine-Tuning for Segment Anything Model

Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation

Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction