Picture for Zhilong Ji

Zhilong Ji

Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization

Add code
May 31, 2024
Viaarxiv icon

MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning

Add code
May 13, 2024
Figure 1 for MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning
Figure 2 for MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning
Figure 3 for MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning
Figure 4 for MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning
Viaarxiv icon

MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation

Add code
May 10, 2024
Figure 1 for MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation
Figure 2 for MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation
Figure 3 for MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation
Figure 4 for MasterWeaver: Taming Editability and Identity for Personalized Text-to-Image Generation
Viaarxiv icon

HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention

Add code
Apr 11, 2024
Viaarxiv icon

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation

Add code
Dec 26, 2023
Viaarxiv icon

Decoupled Textual Embeddings for Customized Image Generation

Add code
Dec 19, 2023
Viaarxiv icon

Patch Is Not All You Need

Add code
Aug 21, 2023
Viaarxiv icon

Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition

Add code
Aug 21, 2023
Viaarxiv icon

Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis

Add code
May 31, 2023
Figure 1 for Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Figure 2 for Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Figure 3 for Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Figure 4 for Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Viaarxiv icon

Masked and Permuted Implicit Context Learning for Scene Text Recognition

Add code
May 25, 2023
Figure 1 for Masked and Permuted Implicit Context Learning for Scene Text Recognition
Figure 2 for Masked and Permuted Implicit Context Learning for Scene Text Recognition
Figure 3 for Masked and Permuted Implicit Context Learning for Scene Text Recognition
Figure 4 for Masked and Permuted Implicit Context Learning for Scene Text Recognition
Viaarxiv icon