Zilong Huang

papers

2,790

total citations

papers (14)

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

CVPR 2020arXiv

196

citations

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

CVPR 2025arXiv

121

citations

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

CVPR 2025arXiv

citations

Human De-Occlusion: Invisible Perception and Recovery for Humans

CVPR 2021arXiv

citations

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

ICLR 2025arXiv

citations

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

ICCV 2025arXiv

citations

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

ICCV 2025arXiv

citations

Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations

NEURIPS 2022arXiv

citations

Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration

CVPR 2025arXiv

citations

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

NEURIPS 2025arXiv

citations

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

ICCV 2025

citations

Zilong Huang

papers (14)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Executing Your Commands via Motion Diffusion in Latent Space

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

Human De-Occlusion: Invisible Perception and Recovery for Humans

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations

Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

papers (14)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Executing Your Commands via Motion Diffusion in Latent Space

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

Human De-Occlusion: Invisible Perception and Recovery for Humans

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations

Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing