Zhen Liu

papers

855

total citations

papers (21)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

NEURIPS 2023arXiv

221

citations

Ghost-Free High Dynamic Range Imaging with Context-Aware Transformer

ECCV 2022arXiv

104

citations

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

CVPR 2024arXiv

citations

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

ICCV 2023arXiv

citations

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

AAAI 2025arXiv

citations

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

CVPR 2025arXiv

citations

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

ICLR 2024arXiv

citations

Learning to See in the Extremely Dark

ICCV 2025arXiv

citations

Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues

ICCV 2025arXiv

citations

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

NEURIPS 2023

citations

Uncertainty-Aware Yield Prediction with Multimodal Molecular Features

AAAI 2024

citations

Zhen Liu

papers (21)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Ghost-Free High Dynamic Range Imaging with Context-Aware Transformer

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

Orthogonal Over-Parameterized Training

DINER: Disorder-Invariant Implicit Neural Representation

Regularizing Neural Networks via Minimizing Hyperspherical Energy

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Minimum Latency Deep Online Video Stabilization

Diffusion Language-Shapelets for Semi-supervised Time-Series Classification

Iterative Teaching by Label Synthesis

Structural Causal 3D Reconstruction

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Learning to See in the Extremely Dark

Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

Uncertainty-Aware Yield Prediction with Multimodal Molecular Features

papers (21)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Ghost-Free High Dynamic Range Imaging with Context-Aware Transformer

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

Orthogonal Over-Parameterized Training

DINER: Disorder-Invariant Implicit Neural Representation

Regularizing Neural Networks via Minimizing Hyperspherical Energy

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Minimum Latency Deep Online Video Stabilization

Diffusion Language-Shapelets for Semi-supervised Time-Series Classification

Iterative Teaching by Label Synthesis

Structural Causal 3D Reconstruction

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Learning to See in the Extremely Dark

Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

Uncertainty-Aware Yield Prediction with Multimodal Molecular Features