Picture for Zhenye Gan

Zhenye Gan

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

Add code
Mar 12, 2025
Viaarxiv icon

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Add code
Mar 09, 2025
Viaarxiv icon

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation

Add code
Dec 30, 2024
Figure 1 for SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
Figure 2 for SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
Figure 3 for SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
Figure 4 for SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
Viaarxiv icon

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

Add code
Nov 24, 2024
Figure 1 for MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Figure 2 for MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Figure 3 for MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Figure 4 for MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Viaarxiv icon

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models

Add code
Oct 21, 2024
Viaarxiv icon

LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description

Add code
Aug 09, 2024
Viaarxiv icon

PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision

Add code
Jul 09, 2024
Figure 1 for PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
Figure 2 for PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
Figure 3 for PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
Figure 4 for PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
Viaarxiv icon

ADer: A Comprehensive Benchmark for Multi-class Visual Anomaly Detection

Add code
Jun 06, 2024
Viaarxiv icon

Efficient Multimodal Large Language Models: A Survey

Add code
May 17, 2024
Figure 1 for Efficient Multimodal Large Language Models: A Survey
Figure 2 for Efficient Multimodal Large Language Models: A Survey
Figure 3 for Efficient Multimodal Large Language Models: A Survey
Figure 4 for Efficient Multimodal Large Language Models: A Survey
Viaarxiv icon

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection

Add code
Apr 14, 2024
Figure 1 for MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Figure 2 for MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Figure 3 for MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Figure 4 for MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Viaarxiv icon