Xu Han

17

Papers

118

Total Citations

Papers (17)

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Predicting Emergent Abilities with Infinite Resolution Evaluation

Progressive Compositionality in Text-to-Image Generative Models

MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models

Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables

Exploring the Benefit of Activation Sparsity in Pre-training

Networks for Joint Affine and Non-Parametric Image Registration

Visual Distant Supervision for Scene Graph Generation

Local Temperature Scaling for Probability Calibration

SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds

MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning

HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss

More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding

patchDPCC: A Patchwise Deep Compression Framework for Dynamic Point Clouds

H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training

Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model