188 citations · 263 across the 12 of their papers we have counts for
14 papers
DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos
Bomiao Wang, Zekai Shao, Jiexiang Lan +3
While MLLMs have made significant strides in chart comprehension and video understanding, current evaluations largely isolate these capabilities, leaving a critical gap in understa…
DeepConnect: A Visual Analytics System for Bridging Interdisciplinary Research Collaborations
Yingchaojie Feng, Zekai Shao, Yiqun Sun +2
Interdisciplinary research collaboration is crucial for scientific innovation, but it remains difficult to initiate in practice. Existing collaborator discovery approaches are ofte…
ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation
Zhenghan Chen, Zekai Shao, Lidan Tan +10
Annotations are essential to communicative visualization, helping explain data, emphasize key findings, and guide attention. While multimodal large language models (MLLMs) offer ne…
ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models
Fen Wang, Zekai Shao, Qiman Kang +5
Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimodal large language mo…
From to : Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
Xiaoliang Fu, Jiaye Lin, Yangyi Fang +6
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithm…
NotebookRAG: Retrieving Multiple Notebooks to Augment the Generation of EDA Notebooks for Crowd-Wisdom
Yi Shan, Yixuan He, Zekai Shao +2
High-quality exploratory data analysis (EDA) is essential in the data science pipeline, but remains highly dependent on analysts' expertise and effort. While recent LLM-based appro…
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Xiaoliang Fu, Jiaye Lin, Yangyi Fang +7
Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms that are fundamentally misali…
Do Language Model Agents Align with Humans in Rating Visualizations? An Empirical Study
Zekai Shao, Yi Shan, Yixuan He +6
Large language models encode knowledge in various domains and demonstrate the ability to understand visualizations. They may also capture visualization design knowledge and potenti…
Unlocking Scientific Concepts: How Effective Are LLM-Generated Analogies for Student Understanding and Classroom Practice?
Zekai Shao, Siyu Yuan, Lin Gao +3
Teaching scientific concepts is essential but challenging, and analogies help students connect new concepts to familiar ideas. Advancements in large language models (LLMs) enable g…
ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset
Fen Wang, Bomiao Wang, Xueli Shu +4
Effective chart summary can significantly reduce the time and effort decision makers spend interpreting charts, enabling precise and efficient communication of data insights. Previ…
Narrative Player: Reviving Data Narratives with Visuals
Zekai Shao, Leixian Shen, Haotian Li +4
Data-rich documents are commonly found across various fields such as business, finance, and science. However, a general limitation of these documents for reading is their reliance…
Fine-Tuned Large Language Model for Visualization System: A Study on Self-Regulated Learning in Education
Lin Gao, Jing Lu, Zekai Shao +7
Large Language Models (LLMs) have shown great potential in intelligent visualization systems, especially for domain-specific applications. Integrating LLMs into visualization syste…
LEVA: Using Large Language Models to Enhance Visual Analytics
Yuheng Zhao, Yixing Zhang, Yu Zhang +5
Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to rec…
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Junjie Ye, Xuanting Chen, Nuo Xu +12
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities. Howe…