5 papers
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
Xiangxi Zheng, Kuang He, Jiayi Hu +6
Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by…
CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
Zhijiang Tang, Linhua Wang, Jiaxin Qi +4
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references. Because human…
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
Pengfei Yue, Xingran Zhao, Juntao Chen +6
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on…
MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models
Yongshun Zhang, Zhongyi Fan, Yonghang Zhang +6
In recent years, large-scale generative models for visual content (\textit{e.g.,} images, videos, and 3D objects/scenes) have made remarkable progress. However, training large-scal…
RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
Wenxu Qian, Chaoyue Wang, Hou Peng +3
Video generation techniques have achieved remarkable advancements in visual quality, yet faithfully reproducing real-world physics remains elusive. Preference-based model post-trai…