Yuning Chai

papers

5,301

total citations

papers (11)

Scalability in Perception for Autonomous Driving: Waymo Open Dataset

CVPR 2020arXiv

3,690

citations

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

ICCV 2021arXiv

743

citations

To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels

CVPR 2021arXiv

citations

HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

CVPR 2021arXiv

citations

Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

ICCV 2023arXiv

citations

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

ICCV 2023arXiv

citations

Reading Recognition in the Wild

NEURIPS 2025arXiv

citations

Yuning Chai

papers (11)

Scalability in Perception for Autonomous Driving: Waymo Open Dataset

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

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving

To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels

HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

Reading Recognition in the Wild

papers (11)

Scalability in Perception for Autonomous Driving: Waymo Open Dataset

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

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving

To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels

HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

Reading Recognition in the Wild