Shangqian Gao

PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs

Pruning Without Fine-Tuning: Dynamic Pruning of Autoregressive Image Generation Models to Mixtures of Experts

MoDeGPT: Modular Decomposition for Large Language Model Compression

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

Cost-Aware Contrastive Routing for LLMs

Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data