Baochang Zhang

Light of Normals: Unified Feature Representation for Universal Photometric Stereo

AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation

RelitTrellis: Lightning-homogenized Structured 3D Latents For Relightable 3D Generation

UrbanGS: Efficient and Scalable Architecture for Geometrically Accurate Large-Scene Reconstruction

CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction

SGR-Q: Saliency-Guided Rescaling for Large Language Model Quantization

JARA: Joint Alignment and Reconstruction Architecture for Region-Aware Vision-Language Pretraining

Surf3R: Rapid Surface Reconstruction from Sparse RGB Views in Seconds

DAMamba: Vision State Space Model with Dynamic Adaptive Scan

Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training

Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection

IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts

CLAD: A Contrastive Learning based Method for Multi-Class Anomaly Detection