Dongfang Liu

papers

1,057

total citations

papers (21)

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

ICCV 2025arXiv

citations

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

ECCV 2022arXiv

citations

Image Translation as Diffusion Visual Programmers

ICLR 2024arXiv

citations

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

ECCV 2024arXiv

citations

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

ICML 2024arXiv

citations

Prototypical Transformer As Unified Motion Learners

ICML 2024arXiv

citations

ProMotion: Prototypes As Motion Learners

CVPR 2024arXiv

citations

All You Need is One: Capsule Prompt Tuning with a Single Vector

NEURIPS 2025arXiv

citations

Probabilistic Token Alignment for Large Language Model Fusion

NEURIPS 2025arXiv

citations

Robust Ego-Exo Correspondence with Long-Term Memory

NEURIPS 2025arXiv

citations

ClusterFomer: Clustering As A Universal Visual Learner

NEURIPS 2023

citations

Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks

ICCV 2021

citations

Dongfang Liu

papers (21)

SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation

TF-Blender: Temporal Feature Blender for Video Object Detection

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning

Learning Equivariant Segmentation with Instance-Unique Querying

Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval

TransFlow: Transformer As Flow Learner

Visual Agents as Fast and Slow Thinkers

Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Image Translation as Diffusion Visual Programmers

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

Prototypical Transformer As Unified Motion Learners

ProMotion: Prototypes As Motion Learners

All You Need is One: Capsule Prompt Tuning with a Single Vector

Probabilistic Token Alignment for Large Language Model Fusion

Robust Ego-Exo Correspondence with Long-Term Memory

ClusterFomer: Clustering As A Universal Visual Learner

Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks

papers (21)

SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation

TF-Blender: Temporal Feature Blender for Video Object Detection

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning

Learning Equivariant Segmentation with Instance-Unique Querying

Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval

TransFlow: Transformer As Flow Learner

Visual Agents as Fast and Slow Thinkers

Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Image Translation as Diffusion Visual Programmers

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

Prototypical Transformer As Unified Motion Learners

ProMotion: Prototypes As Motion Learners

All You Need is One: Capsule Prompt Tuning with a Single Vector

Probabilistic Token Alignment for Large Language Model Fusion

Robust Ego-Exo Correspondence with Long-Term Memory

ClusterFomer: Clustering As A Universal Visual Learner

Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks