Yulun Zhang

Associate Professor@Shanghai Jiaotong University·中国·OpenReview

研究方向

Large Language Models · Model Compression · Model Quantization · Model Pruning · Medical Image Analysis · Image Style Transfer · Image Quality Assessment · Image Restoration · Image Super-Resolution

Yulun Zhang

Quantized Visual Geometry Grounded Transformer

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models

FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization

InfVSR: Breaking Length Limits of Generic Video Super-Resolution

Progressive Binarization with Semi-Structured Pruning for LLMs

CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution

DVD-Quant: Data-free Video Diffusion Transformers Quantization

Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution

PT$^2$-LLM: Post-Training Ternarization for Large Language Models

ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration

RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement

VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement

Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction

Asymmetric VAE for One-Step Video Super-Resolution Acceleration

RectiWeather: Photo-Realistic Adverse Weather Removal via Zero-shot Soft Weather Perception and Rectified Flow

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

AdaSVD: Adaptive Singular Value Decomposition for Large Language Models

QuantDemoire: Quantization with Outlier Aware for Image Demoiréing

CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers

LLM-IQA: Standard-guided MLLM for Mix-grained Image Quality Assessment

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

RUN: Reversible Unfolding Network for Concealed Object Segmentation

Human Body Restoration with One-Step Diffusion Model and A New Benchmark

ARB-LLM: Alternating Refined Binarizations for Large Language Models

Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data

Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher

One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation

BiDRN: Binarized 3D Whole-body Human Mesh Recovery

Low-bit Quantization for Seeing in the Dark

Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution

Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution

Image Super-Resolution with Text Prompt Diffusion

Integrating State Space Model and Transformer for Global-Local Processing in Super-Resolution Networks

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