Wenxiao Wang

18

Papers

99

Total Citations

Papers (18)

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

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

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

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

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

On Feature Decorrelation in Self-Supervised Learning

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

One-shot Implicit Animatable Avatars with Model-based Priors

Masked Autoencoders for Point Cloud Self-Supervised Learning

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

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

Learning Occupancy for Monocular 3D Object Detection

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

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

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

Lethal Dose Conjecture on Data Poisoning

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

Temporal Robustness against Data poisoning