Chenxi Liu

18

Papers

26

Total Citations

Papers (18)

De-Diffusion Makes Text a Strong Cross-Modal Interface

A Watermark for Order-Agnostic Language Models

Rent3D: Floor-Plan Priors for Monocular Layout Estimation

Few-Shot Image Recognition by Predicting Parameters From Activations

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions

Adversarial Attacks Beyond the Image Space

Progressive Stage-Wise Learning for Unsupervised Feature Representation Enhancement

MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences

Recurrent Multimodal Interaction for Referring Image Segmentation

SORT: Second-Order Response Transform for Visual Recognition

ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond

Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion Dataset

Are Labels Necessary for Neural Architecture Search?

SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds

Federated Continuous Category Discovery and Learning

LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment