13 papers · 1 filter
Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation
Sujie Hu, Huaisong Zhang, Pujing Yang +7
Recent reinforcement learning approaches have improved visual text generation, yet generated images still suffer from incorrect wording and malformed glyphs. We identify two couple…
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
Xingsong Ye, Yongkun Du, Jiaxin Zhang +6
Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages and the difficulty of serving diverse scripts within a single…
Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding
Haotian Dong, Wenjing Wang, Chen Li +3
Looping videos are essential for practical applications such as web graphics, game development, and social media. However, existing approaches typically fail to generate high-quali…
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
Xingsong Ye, Yongkun Du, Jiaxin Zhang +5
WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general…
WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization
Qian Liang, Xiaomin Li, Ying Zhang +6
Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can ev…
What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution
Xingsong Ye, Yongkun Du, JiaXin Zhang +3
Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Syntheti…
FireRed-Image-Edit-1.0 Technical Report
Super Intelligence Team, Changhao Qiao, Chao Hui +16
We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curati…
FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
Yeyao Ma, Chen Li, Xiaosong Zhang +2
Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning m…
StableWorld: Towards Stable and Consistent Long Interactive Video Generation
Ying Yang, Zhengyao Lv, Yujia Zeng +9
In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds th…
DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation
Ying Yang, Zhengyao Lv, Tianlin Pan +5
In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors…
FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
Lei Ke, Hubery Yin, Gongye Liu +6
With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, Re…
Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
Haotian Dong, Wenjing Wang, Chen Li +2
Generating RGB-A videos, which include alpha channels for transparency, has wide applications. However, current methods often suffer from low quality due to confusion between RGB a…
Detecting Adversarial Data using Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo +4
As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution…