Picture for Xiang Fu

Xiang Fu

Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching

Add code
Apr 16, 2025
Viaarxiv icon

M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning in Large Vision-Language Models

Add code
Apr 06, 2025
Viaarxiv icon

A practical guide to machine learning interatomic potentials -- Status and future

Add code
Mar 12, 2025
Viaarxiv icon

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

Add code
Mar 05, 2025
Viaarxiv icon

Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction

Add code
Feb 17, 2025
Viaarxiv icon

CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening

Add code
Jan 11, 2025
Figure 1 for CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
Figure 2 for CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
Figure 3 for CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
Figure 4 for CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
Viaarxiv icon

Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models

Add code
Oct 16, 2024
Figure 1 for Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Figure 2 for Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Figure 3 for Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Figure 4 for Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Viaarxiv icon

High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures

Add code
Aug 01, 2024
Figure 1 for High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
Figure 2 for High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
Figure 3 for High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
Figure 4 for High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
Viaarxiv icon

Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates

Add code
Jul 05, 2024
Viaarxiv icon

A Recipe for Charge Density Prediction

Add code
May 29, 2024
Viaarxiv icon