Picture for Qing Lian

Qing Lian

The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs

Add code
Feb 06, 2024
Viaarxiv icon

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

Add code
Jan 17, 2024
Viaarxiv icon

R-Tuning: Teaching Large Language Models to Refuse Unknown Questions

Add code
Nov 16, 2023
Figure 1 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 2 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 3 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 4 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Viaarxiv icon

Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing

Oct 17, 2023
Viaarxiv icon

MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning

Sep 18, 2023
Figure 1 for MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning
Figure 2 for MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning
Figure 3 for MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning
Figure 4 for MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning
Viaarxiv icon

Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning

Sep 05, 2023
Figure 1 for Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning
Figure 2 for Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning
Figure 3 for Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning
Figure 4 for Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning
Viaarxiv icon

Adv3D: Generating 3D Adversarial Examples in Driving Scenarios with NeRF

Add code
Sep 04, 2023
Viaarxiv icon

DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking

Add code
Apr 19, 2023
Figure 1 for DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
Figure 2 for DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
Figure 3 for DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
Figure 4 for DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking
Viaarxiv icon

Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field

Add code
Apr 07, 2023
Figure 1 for Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
Figure 2 for Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
Figure 3 for Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
Figure 4 for Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
Viaarxiv icon

MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones

Add code
Jul 26, 2022
Figure 1 for MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
Figure 2 for MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
Figure 3 for MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
Figure 4 for MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
Viaarxiv icon