Xiangyang Xue

MouseDTB: A Mouse Digital Twin Brain at Single-neuron Resolution

Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View

TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot Control

Chinese Character Decomposition with Compositional Latent Components

Local Distribution-Conditioned Image Synthesis for One-Shot Federated Learning

Decomposition of Concept-Level Rules in Visual Scenes

DynTopo: Dynamic Topological Scene Graph for Robotic Autonomy in Human-Centric Environments

VidSplice: Towards Coherent Video Inpainting via Explicit Spaced Frame Guidance

Learning Global Representaion from Queries for Vectorized HD Map Construction

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning