5 papers
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Zhaowei Wang, Lishu Luo, Haodong Duan +9
Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video…
Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
Xingyue Lin, Shuai Peng, Xiangyu Xie +3
Image vectorization aims to convert raster images into editable, scalable vector representations while preserving visual fidelity. Existing vectorization methods struggle to repres…
Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition
Yu Li, Jin Jiang, Jianhua Zhu +4
Handwritten Mathematical Expression Recognition (HMER) remains a persistent challenge in Optical Character Recognition (OCR) due to the inherent freedom of symbol layouts and varia…
LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
Jin Jiang, Yuchen Yan, Yang Liu +6
In this paper, we propose a new data synthesis method called \textbf{LogicPro}, which leverages LeetCode-style algorithm \underline{Pro}blems and their corresponding \underline{Pro…
SketchRef: a Multi-Task Evaluation Benchmark for Sketch Synthesis
Xingyue Lin, Xingjian Hu, Shuai Peng +2
Sketching is a powerful artistic technique for capturing essential visual information about real-world objects and has increasingly attracted attention in image synthesis research.…