Hongxia Jin

MoDeGPT: Modular Decomposition for Large Language Model Compression

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior

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

Uncertainty-aware Fine-tuning on Time Series Foundation Model for Anomaly Detection

Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark

AlpaGasus: Training a Better Alpaca with Fewer Data

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models

CIFD: Controlled Information Flow to Enhance Knowledge Distillation

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

Instruction-following Evaluation through Verbalizer Manipulation