Yue Zhao

Affiliations

UT Austin

papers

2,607

total citations

papers (28)

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

NEURIPS 2022arXiv

138

citations

Omni-sourced Webly-supervised Learning for Video Recognition

ECCV 2020arXiv

101

citations

Real-Time Online Video Detection with Temporal Smoothing Transformers

ECCV 2022arXiv

citations

On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks

CVPR 2020arXiv

citations

Intra- and Inter-Action Understanding via Temporal Action Parsing

CVPR 2020arXiv

citations

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

ICLR 2024arXiv

citations

VideoPrism: A Foundational Visual Encoder for Video Understanding

ICML 2024arXiv

citations

One-Minute Video Generation with Test-Time Training

CVPR 2025arXiv

citations

PointBA: Towards Backdoor Attacks in 3D Point Cloud

ICCV 2021arXiv

citations

ADGym: Design Choices for Deep Anomaly Detection

NEURIPS 2023arXiv

citations

Bayesian Diffusion Models for 3D Shape Reconstruction

CVPR 2024arXiv

citations

BA-Net: Bridge Attention for Deep Convolutional Neural Networks

ECCV 2022arXiv

citations

Distilling Vision-Language Models on Millions of Videos

CVPR 2024arXiv

citations

RayZer: A Self-supervised Large View Synthesis Model

ICCV 2025arXiv

citations

MetaOOD: Automatic Selection of OOD Detection Models

ICLR 2025arXiv

citations

DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection

CVPR 2025arXiv

citations

Distilling Structural Representations into Protein Sequence Models

ICLR 2025

citations

Secure On-Device Video OOD Detection Without Backpropagation

ICCV 2025arXiv

citations

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

CVPR 2025arXiv

citations

Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

ICML 2024arXiv

citations

Position: TrustLLM: Trustworthiness in Large Language Models

ICML 2024

citations

TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation

CVPR 2021

citations

Automatic Unsupervised Outlier Model Selection

NEURIPS 2021

citations

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

COLM 2025arXiv

citations

Yue Zhao

Affiliations

papers (28)

Revisiting Skeleton-Based Action Recognition

FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding

ADBench: Anomaly Detection Benchmark

Learning Video Representations From Large Language Models

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

Omni-sourced Webly-supervised Learning for Video Recognition

Real-Time Online Video Detection with Temporal Smoothing Transformers

On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks

Intra- and Inter-Action Understanding via Temporal Action Parsing

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

VideoPrism: A Foundational Visual Encoder for Video Understanding

One-Minute Video Generation with Test-Time Training

PointBA: Towards Backdoor Attacks in 3D Point Cloud

ADGym: Design Choices for Deep Anomaly Detection

Bayesian Diffusion Models for 3D Shape Reconstruction

BA-Net: Bridge Attention for Deep Convolutional Neural Networks

Distilling Vision-Language Models on Millions of Videos

RayZer: A Self-supervised Large View Synthesis Model

MetaOOD: Automatic Selection of OOD Detection Models

DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection

Distilling Structural Representations into Protein Sequence Models

Secure On-Device Video OOD Detection Without Backpropagation

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

Position: TrustLLM: Trustworthiness in Large Language Models

TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation

Automatic Unsupervised Outlier Model Selection

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

papers (28)

Revisiting Skeleton-Based Action Recognition

FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding

ADBench: Anomaly Detection Benchmark

Learning Video Representations From Large Language Models

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

Omni-sourced Webly-supervised Learning for Video Recognition

Real-Time Online Video Detection with Temporal Smoothing Transformers

On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks

Intra- and Inter-Action Understanding via Temporal Action Parsing

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

VideoPrism: A Foundational Visual Encoder for Video Understanding

One-Minute Video Generation with Test-Time Training

PointBA: Towards Backdoor Attacks in 3D Point Cloud

ADGym: Design Choices for Deep Anomaly Detection

Bayesian Diffusion Models for 3D Shape Reconstruction

BA-Net: Bridge Attention for Deep Convolutional Neural Networks

Distilling Vision-Language Models on Millions of Videos

RayZer: A Self-supervised Large View Synthesis Model

MetaOOD: Automatic Selection of OOD Detection Models

DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection

Distilling Structural Representations into Protein Sequence Models

Secure On-Device Video OOD Detection Without Backpropagation

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

Position: TrustLLM: Trustworthiness in Large Language Models

TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation

Automatic Unsupervised Outlier Model Selection

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model