41 citations · 76 across the 17 of their papers we have counts for
20 papers
TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering
Yiyang Chen, Guo-Hua Wang, Yaoli Liu +4
Text-to-image models increasingly generate readable Chinese text that still contains local rendering defects, such as a character with an extra or missing stroke or a malformed com…
Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation
Yaoli Liu, Guo-Hua Wang, Yiyang Chen +4
Generated images often have coherent layouts and visual content, yet local errors in small text and complex characters still limit their readability and practical use. Scene-text r…
Training-Free Image Editing with Visual Context Integration and Concept Alignment
Rui Song, Guo-Hua Wang, Qing-Guo Chen +6
In image editing, it is essential to incorporate a context image to convey the user's precise requirements, such as subject appearance or image style. Existing training-based visua…
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
Minghao Fu, Guo-Hua Wang, Tianyu Cui +4
Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization…
Ovis-Image Technical Report
Guo-Hua Wang, Liangfu Cao, Tianyu Cui +8
We introduce , a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational c…
Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
Jie Shao, Ke Zhu, Minghao Fu +2
Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate dist…
TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance
Minghao Fu, Guo-Hua Wang, Xiaohao Chen +4
Recent advances in text-to-image synthesis largely benefit from sophisticated sampling strategies and classifier-free guidance (CFG) to ensure high-quality generation. However, CFG…
Ovis-U1 Technical Report
Guo-Hua Wang, Shanshan Zhao, Xinjie Zhang +9
In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Buildi…
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
Shanshan Zhao, Xinjie Zhang, Jintao Guo +9
Recent years have seen remarkable progress in both multimodal understanding models and image generation models. Despite their respective successes, these two domains have evolved i…
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
Minghao Fu, Guo-Hua Wang, Liangfu Cao +4
Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial…
Evaluating Image Caption via Cycle-consistent Text-to-Image Generation
Tianyu Cui, Jinbin Bai, Guo-Hua Wang +5
Evaluating image captions typically relies on reference captions, which are costly to obtain and exhibit significant diversity and subjectivity. While reference-free evaluation met…
Dense Vision Transformer Compression with Few Samples
Hanxiao Zhang, Yifan Zhou, Guo-Hua Wang +1
Few-shot model compression aims to compress a large model into a more compact one with only a tiny training set (even without labels). Block-level pruning has recently emerged as a…
Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm
Guo-Hua Wang, Jianxin Wu
Due to data privacy issues, accelerating networks with tiny training sets has become a critical need in practice. Previous methods achieved promising results empirically by filter-…
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Guo-Hua Wang, Jiahao Li, Bin Li +1
Neural image compression has surpassed state-of-the-art traditional codecs (H.266/VVC) for rate-distortion (RD) performance, but suffers from large complexity and separate models f…
How to Reduce Change Detection to Semantic Segmentation
Guo-Hua Wang, Bin-Bin Gao, Chengjie Wang
Change detection (CD) aims to identify changes that occur in an image pair taken different times. Prior methods devise specific networks from scratch to predict change masks in pix…
R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning
Guo-Hua Wang, Jianxin Wu
Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parame…
PENCIL: Deep Learning with Noisy Labels
Kun Yi, Guo-Hua Wang, Jianxin Wu
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with n…
Practical Network Acceleration with Tiny Sets
Guo-Hua Wang, Jianxin Wu
Due to data privacy issues, accelerating networks with tiny training sets has become a critical need in practice. Previous methods mainly adopt filter-level pruning to accelerate n…
Distilling Knowledge by Mimicking Features
Guo-Hua Wang, Yifan Ge, Jianxin Wu
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's s…
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
Guo-Hua Wang, Jianxin Wu
Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parame…