10 papers · 1 filter
Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
Pengyu Li, Zhitao Gao, Lingling Zhang +4
Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference co…
ChartAct: A Benchmark for Dynamic Chart Understanding
Muye Huang, Lin Wu, Lingling Zhang +5
Charts are widely used to present complex data for analysis and decision making. Existing chart understanding benchmarks mainly focus on static charts, but real-world charts are of…
Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion
Bo Li, Yunkuo Lei, Tingting Bao +5
Multi-focus image fusion (MFIF) is a crucial technique in image processing, with a key challenge being the generation of decision maps with precise boundaries. However, traditional…
SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More
Muye Huang, Lingling Zhang, Yifei Li +2
Charts are high-density visual carriers of complex data and medium for information extraction and analysis. Due to the need for precise and complex visual reasoning, automated char…
CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
Xinyu Zhang, Yuxuan Dong, Lingling Zhang +5
Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrele…
Diagram-Driven Course Questions Generation
Xinyu Zhang, Lingling Zhang, Yanrui Wu +6
Visual Question Generation (VQG) research focuses predominantly on natural images while neglecting the diagram, which is a critical component in educational materials. To meet the…