Jie Hu

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models

Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing

An Empirical Study of Extremely Low-Bit Quantization for Large Language Models

RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration

DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution

CBQ: Cross-Block Quantization for Large Language Models

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Multi-Granularity Semantic Revision for Large Language Model Distillation

One Step Diffusion-based Super-Resolution with Time-Aware Distillation

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training

Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution