Yujie Zhong

12

Papers

58

Total Citations

Papers (12)

UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection

Mr. DETR: Instructive Multi-Route Training for Detection Transformers

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models

RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving

HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver

RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case

v-CLR: View-Consistent Learning for Open-World Instance Segmentation

InstaGen: Enhancing Object Detection by Training on Synthetic Dataset

Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs

DisTime: Distribution-based Time Representation for Video Large Language Models

Advancing Visual Large Language Model for Multi-granular Versatile Perception

Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models