22 citations · 31 across the 21 of their papers we have counts for
7 papers · 1 filter
CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs
Jiahui Kang, Bifan Wei, Lingling Zhang +4
Despite significant progress in visual tasks by Multimodal Large Language Models (MLLMs), geometric diagram understanding remains challenging due to the presence of sparse visual c…
DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction
Muye Huang, Lingling Zhang, Xingyu Yu +7
Human interaction is continuous, multimodal, and full-duplex by nature. Although recent omni models have made substantial progress in unified speech, vision, and text modeling, com…
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…
ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion
Bo Li, Tingting Bao, Lingling Zhang +3
Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is tha…
ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics
Weiping Fu, Bifan Wei, Jingyi Hao +7
Automatic Question Generation (QG) often produces outputs with critical defects, such as factual hallucinations and answer mismatches. However, existing evaluation methods, includi…
MAXS: Meta-Adaptive Exploration with LLM Agents
Jian Zhang, Zhiyuan Wang, Zhangqi Wang +7
Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer f…
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…