Shiyi Lan

15

Papers

170

Total Citations

Papers (15)

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?

MDP: Multidimensional Vision Model Pruning with Latency Constraint

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

FastMask: Segment Multi-Scale Object Candidates in One Shot

Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN

SaccadeNet: A Fast and Accurate Object Detector

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

Vision Transformers Are Good Mask Auto-Labelers

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

Fully Attentional Networks with Self-emerging Token Labeling

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning