7 papers
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Ruilin Luo, Chufan Shi, Yizhen Zhang +10
The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this…
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
Tongkun Guan, Zhibo Yang, Jianqiang Wan +10
When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limit…
SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild
Jiawei Liu, Yuanzhi Zhu, Feiyu Gao +5
Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, c…
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy
Zhibo Yang, Jun Tang, Zhaohai Li +9
Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what exten…
VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer
Humen Zhong, Zhibo Yang, Zhaohai Li +4
Text recognition is an inherent integration of vision and language, encompassing the visual texture in stroke patterns and the semantic context among the character sequences. Towar…
Platypus: A Generalized Specialist Model for Reading Text in Various Forms
Peng Wang, Zhaohai Li, Jun Tang +4
Reading text from images (either natural scenes or documents) has been a long-standing research topic for decades, due to the high technical challenge and wide application range. P…
Visual Text Generation in the Wild
Yuanzhi Zhu, Jiawei Liu, Feiyu Gao +6
Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-…