Xin Huang

13

Papers

94

Total Citations

Papers (13)

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Material Anything: Generating Materials for Any 3D Object via Diffusion

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

Improved Maximin Share Approximations for Chores by Bin Packing

Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images

Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

Causal Composition Diffusion Model for Closed-loop Traffic Generation

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

Privileged Prior Information Distillation for Image Matting

G2L-CariGAN: Caricature Generation from Global Structure to Local Features