Picture for Yongdong Zhang

Yongdong Zhang

DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection

Add code
May 16, 2024
Viaarxiv icon

Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming

Add code
Apr 19, 2024
Figure 1 for Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Figure 2 for Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Figure 3 for Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Figure 4 for Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Viaarxiv icon

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation

Add code
Apr 08, 2024
Figure 1 for AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
Figure 2 for AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
Viaarxiv icon

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

Add code
Mar 12, 2024
Figure 1 for DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
Figure 2 for DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
Figure 3 for DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
Figure 4 for DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
Viaarxiv icon

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization

Add code
Mar 01, 2024
Figure 1 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 2 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 3 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 4 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Viaarxiv icon

Alleviating Structural Distribution Shift in Graph Anomaly Detection

Add code
Jan 25, 2024
Viaarxiv icon

Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification

Add code
Jan 04, 2024
Figure 1 for Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification
Figure 2 for Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification
Figure 3 for Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification
Figure 4 for Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification
Viaarxiv icon

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences

Add code
Nov 23, 2023
Figure 1 for ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
Figure 2 for ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
Figure 3 for ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
Figure 4 for ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
Viaarxiv icon

Grammatical Error Correction via Mixed-Grained Weighted Training

Add code
Nov 23, 2023
Viaarxiv icon

On the Calibration of Large Language Models and Alignment

Add code
Nov 22, 2023
Viaarxiv icon