Wenxiao Wang

Affiliations

Zhejiang University

papers

2,038

total citations

papers (19)

Masked Autoencoders for Point Cloud Self-Supervised Learning

ECCV 2022arXiv

638

citations

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

CVPR 2020arXiv

488

citations

On Feature Decorrelation in Self-Supervised Learning

ICCV 2021arXiv

225

citations

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

CVPR 2023arXiv

189

citations

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

ECCV 2022arXiv

citations

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

ICML 2024arXiv

citations

Learning Occupancy for Monocular 3D Object Detection

CVPR 2024arXiv

citations

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

NEURIPS 2023arXiv

citations

Lethal Dose Conjecture on Data Poisoning

NEURIPS 2022arXiv

citations

Temporal Robustness against Data poisoning

NEURIPS 2023arXiv

citations

3426 Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving

AAAI 2024

citations

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

CVPR 2024arXiv

citations

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

ICLR 2024arXiv

citations

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

ECCV 2024arXiv

citations

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction

AAAI 2025

citations

Wenxiao Wang

Affiliations

papers (19)

Masked Autoencoders for Point Cloud Self-Supervised Learning

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

On Feature Decorrelation in Self-Supervised Learning

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection

One-shot Implicit Animatable Avatars with Model-based Priors

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Learning Occupancy for Monocular 3D Object Detection

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

Lethal Dose Conjecture on Data Poisoning

Temporal Robustness against Data poisoning

3426 Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction

papers (19)

Masked Autoencoders for Point Cloud Self-Supervised Learning

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

On Feature Decorrelation in Self-Supervised Learning

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection

One-shot Implicit Animatable Avatars with Model-based Priors

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Learning Occupancy for Monocular 3D Object Detection

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

Lethal Dose Conjecture on Data Poisoning

Temporal Robustness against Data poisoning

3426 Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction