Picture for Wei Ji

Wei Ji

Anatomically and Metabolically Informed Diffusion for Unified Denoising and Segmentation in Low-Count PET Imaging

Add code
Mar 17, 2025
Viaarxiv icon

Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model

Add code
Mar 14, 2025
Viaarxiv icon

TAIL: Text-Audio Incremental Learning

Add code
Mar 06, 2025
Viaarxiv icon

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

Add code
Feb 18, 2025
Viaarxiv icon

A Generalizable 3D Diffusion Framework for Low-Dose and Few-View Cardiac SPECT

Add code
Dec 21, 2024
Viaarxiv icon

MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks

Add code
Nov 29, 2024
Viaarxiv icon

Differentiable Gaussian Representation for Incomplete CT Reconstruction

Add code
Nov 07, 2024
Viaarxiv icon

Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach

Add code
Nov 03, 2024
Viaarxiv icon

Grounding is All You Need? Dual Temporal Grounding for Video Dialog

Add code
Oct 08, 2024
Figure 1 for Grounding is All You Need? Dual Temporal Grounding for Video Dialog
Figure 2 for Grounding is All You Need? Dual Temporal Grounding for Video Dialog
Figure 3 for Grounding is All You Need? Dual Temporal Grounding for Video Dialog
Figure 4 for Grounding is All You Need? Dual Temporal Grounding for Video Dialog
Viaarxiv icon

Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation

Add code
Sep 10, 2024
Figure 1 for Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation
Figure 2 for Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation
Figure 3 for Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation
Figure 4 for Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation
Viaarxiv icon