Lu Qi

D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Multi-Object System Identification from Videos

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

CyberV: A Cybernetic Framework for Enhancing Logical Reasoning in Video Understanding

UMC: A Unified Approach for Resilient Control of Legged Robots Across Masked Malfunction Training

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video

RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platfrom for Embodied Intelligence

Seg-VAR:Image Segmentation with Visual Autoregressive Modeling

HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis

RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection

Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset

PredFormer: Transformers Are Effective Spatial-Temporal Predictive Learners

RelationBooth: Towards Relation-Aware Customized Object Generation