Author name cluster

Han Lai

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

NeurIPS Conference 2025 Conference Paper

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

Muye Huang
Lingling Zhang
Jie Ma
Han Lai
Fangzhi Xu
Yifei Li
Wenjun Wu
Yaqiang Wu

Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models (MLLMs) due to the need for precise and complex visual reasoning. Current step-by-step reasoning models primarily focus on text-based logical reasoning for chart understanding. However, they struggle to refine or correct their reasoning when errors stem from flawed visual understanding, as they lack the ability to leverage multimodal interaction for deeper comprehension. Inspired by human cognitive behavior, we propose ChartSketcher, a multimodal feedback-driven step-by-step reasoning method designed to address these limitations. ChartSketcher is a chart understanding model that employs Sketch-CoT, enabling MLLMs to annotate intermediate reasoning steps directly onto charts using a programmatic sketching library, iteratively feeding these visual annotations back into the reasoning process. This mechanism enables the model to visually ground its reasoning and refine its understanding over multiple steps. We employ a two-stage training strategy: a cold start phase to learn sketch-based reasoning patterns, followed by off-policy reinforcement learning to enhance reflection and generalization. Experiments demonstrate that ChartSketcher achieves promising performance on chart understanding benchmarks and general vision tasks, providing an interactive and interpretable approach to chart comprehension.

PDF Details

AAAI Conference 2025 Conference Paper

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Muye Huang
Han Lai
Xinyu Zhang
Wenjun Wu
Jie Ma
Lingling Zhang
Jun Liu

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension abilities in real-world scenarios. Specifically, EvoChart is a unique self-training data synthesis approach that simultaneously produces high-quality training corpus and a high-performance chart understanding model. EvoChart-QA consists of 650 distinct real-world charts collected from 140 different websites and 1,250 expert-curated questions that focus on chart understanding. Experimental results on various open-source and proprietary VLMs tested on EvoChart-QA demonstrate that even the best proprietary model, GPT-4o, achieves only 49.8% accuracy. Moreover, the EvoChart method significantly boosts the performance of open-source VLMs on real-world chart understanding tasks, achieving 54.2% accuracy on EvoChart-QA.

PDF Details DOI

AAAI Conference 2025 Conference Paper

VProChart: Answering Chart Question Through Visual Perception Alignment Agent and Programmatic Solution Reasoning

Muye Huang
Lingling Zhang
Han Lai
Wenjun Wu
Xinyu Zhang
Jun Liu

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to interpret, and chart-related questions often involve complex logical and numerical reasoning, which hinders the performance of existing models. This paper introduces VProChart, a novel framework designed to address these challenges in CQA by integrating a lightweight Visual Perception Alignment Agent (VPAgent) and a Programmatic Solution Reasoning approach. VPAgent aligns and models chart elements based on principles of human visual perception, enhancing the understanding of chart context. The Programmatic Solution Reasoning approach leverages large language models (LLMs) to transform natural language reasoning questions into structured solution programs, facilitating precise numerical and logical reasoning. Extensive experiments on benchmark datasets such as ChartQA and PlotQA demonstrate that VProChart significantly outperforms existing methods, highlighting its capability in understanding and reasoning with charts.

PDF Details DOI

YNIMG Journal 2022 Journal Article

Patterns of a structural covariance network associated with dispositional optimism during late adolescence

Han Lai
Xiangzhen Kong
Yajun Zhao
Nanfang Pan
Xun Zhang
Min He
Song Wang
Qiyong Gong

Dispositional optimism (hereinafter, optimism), as a vital character strength, reflects the tendency to hold generalized positive expectancies for future outcomes. A great number of studies have consistently shown the importance of optimism to a spectrum of physical and mental health outcomes. However, less attention has been given to the intrinsic neurodevelopmental patterns associated with interindividual differences in optimism. Here, we investigated this important question in a large sample comprising 231 healthy adolescents (16-20 years old) via structural magnetic resonance imaging and behavioral tests. We constructed individual structural covariance networks based on cortical gyrification using a recent novel approach combining probability density estimation and Kullback-Leibler divergence and estimated global (global efficiency, local efficiency and small-worldness) and regional (betweenness centrality) properties of these constructed networks using graph theoretical analysis. Partial correlations adjusted for age, sex and estimated total intracranial volume showed that optimism was positively related to global and local efficiency but not small-worldness. Partial least squares correlations indicated that optimism was positively linked to a pronounced betweenness centrality pattern, in which twelve cognition-, emotion-, and motivation-related regions made robust and reliable contributions. These findings remained basically consistent after additionally controlling for family socioeconomic status and showed significant correlations with optimism scores from 2.5 years before, which replicated the main findings. The current work, for the first time, delineated characteristics of the cortical gyrification covariance network associated with optimism, extending previous neurobiological understandings of optimism, which may navigate the development of interventions on a neural network level aimed at raising optimism.

Details DOI

EAAI Journal 2021 Journal Article

A multi-criteria decision making method based on DNMA and CRITIC with linguistic D numbers for blockchain platform evaluation

Han Lai
Huchang Liao

Since more and more blockchain platforms have been utilized in diverse business applications, the blockchain platform evaluation becomes significant for clients. There are challenges regarding the blockchain platform evaluation in terms of information uncertainty, multiple types of criteria, and the correlations between criteria. This study dedicates to proposing a method to solve these problems by integrating linguistic D numbers (LDNs), double normalization-based multiple aggregation (DNMA) method, and Criteria Importance Through Inter-criteria Correlation (CRITIC) method. Firstly, a conversion rule of LDNs is introduced to enhance the comparative rule of LDNs. Then, an integrated multiple criteria decision making framework is proposed by incorporating DNMA with LDNs. This method not only can effectively capture the incomplete or uncertain decision-making information with respect to cost, benefit, and target criteria, but also can reduce the loss of decision information caused by single normalized technology. The CRITIC method is integrated in the LDN-based DNMA method to reflect the correlations between criteria in the blockchain platform evaluation process. To investigate the efficiency of the proposed method, a numerical example of blockchain platform evaluation is given. The sensitivity analysis demonstrates the robustness and stability of the developed method. The comparative analysis shows that our method can identify the potentially important criteria in the decision-making process effectively.

Details DOI