Zhen Dong

papers

1,964

total citations

papers (24)

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

CVPR 2023arXiv

citations

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

ICCV 2021arXiv

citations

Learnable Motion Coherence for Correspondence Pruning

CVPR 2021arXiv

citations

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

ICCV 2021arXiv

citations

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

CVPR 2022arXiv

citations

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

CVPR 2025arXiv

citations

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

ICLR 2025arXiv

citations

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

CVPR 2023arXiv

citations

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

ICCV 2025arXiv

citations

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

AAAI 2024

citations

QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection

ICCV 2023arXiv

citations

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

CVPR 2025arXiv

citations

An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control

AAAI 2025arXiv

citations

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

ICLR 2025

citations

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

ICML 2024arXiv

citations

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

CVPR 2025arXiv

citations

Enhancing Robot Program Synthesis Through Environmental Context

NEURIPS 2023arXiv

citations

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

CVPR 2024

citations

DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis

CVPR 2025

citations

Zhen Dong

papers (24)

ZeroQ: A Novel Zero Shot Quantization Framework

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

SqueezeLLM: Dense-and-Sparse Quantization

Q-Diffusion: Quantizing Diffusion Models

PB-LLM: Partially Binarized Large Language Models

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

Learnable Motion Coherence for Correspondence Pruning

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

Enhancing Robot Program Synthesis Through Environmental Context

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis

papers (24)

ZeroQ: A Novel Zero Shot Quantization Framework

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

SqueezeLLM: Dense-and-Sparse Quantization

Q-Diffusion: Quantizing Diffusion Models

PB-LLM: Partially Binarized Large Language Models

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

Learnable Motion Coherence for Correspondence Pruning

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

Enhancing Robot Program Synthesis Through Environmental Context

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis