Picture for Yao Du

Yao Du

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights

Add code
Mar 06, 2025
Viaarxiv icon

Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging

Add code
Mar 03, 2025
Viaarxiv icon

EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning

Add code
Aug 21, 2024
Figure 1 for EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning
Figure 2 for EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning
Figure 3 for EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning
Figure 4 for EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning
Viaarxiv icon

Teach CLIP to Develop a Number Sense for Ordinal Regression

Add code
Aug 07, 2024
Viaarxiv icon

MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results

Add code
Jun 11, 2024
Figure 1 for MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
Figure 2 for MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
Figure 3 for MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
Figure 4 for MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
Viaarxiv icon

Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications

Add code
Apr 02, 2024
Viaarxiv icon

Sign Language Production with Latent Motion Transformer

Add code
Dec 20, 2023
Figure 1 for Sign Language Production with Latent Motion Transformer
Figure 2 for Sign Language Production with Latent Motion Transformer
Figure 3 for Sign Language Production with Latent Motion Transformer
Figure 4 for Sign Language Production with Latent Motion Transformer
Viaarxiv icon

ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers

Add code
Aug 30, 2023
Viaarxiv icon

Inferring Attracting Basins of Power System with Machine Learning

Add code
May 20, 2023
Viaarxiv icon

Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation

Add code
Aug 19, 2022
Figure 1 for Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation
Figure 2 for Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation
Figure 3 for Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation
Figure 4 for Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation
Viaarxiv icon