Kuang-Da Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kuang-Da Wang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Wen-Chih Peng
National yang Ming Chiao Tung University
12 shared publications - Wei-Yao Wang
Sony Group Corporation, Tokyo, Japan
10 shared publications Boris Ginsburg
NVIDIA
2 shared publicationsChao-Han Huck Yang
NVIDIA
2 shared publications- Cheng-Ming Lin
National yang Ming Chiao Tung University
2 shared publications Ching Chang
National yang Ming Chiao Tung University
2 shared publications
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 570-587
Visual Prompt Discovery via Semantic Exploration
- 10 September 2026
- Published by Springer Nature
- p. 570-587
Visual Prompt Discovery via Semantic Exploration
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9927-9938
WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9927-9938
Open AccessWebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1268-1272
Adapting to Evolving Data: Test-Time Expert Aggregation for Imbalanced Tabular Regression
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1268-1272
Open AccessAdapting to Evolving Data: Test-Time Expert Aggregation for Imbalanced Tabular Regression
- Open Access
- 29 January 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 120 (1) , 11
Multi-Agent Reinforcement Learning Correctable Strategy: A Framework with Correctable Strategies for Portfolio Management
Portfolio management (PM) is a broad investment strategy aimed at risk mitigation through diversified financial product investments. Acknowledging the significance of dynamic adjustments after establishing a portfolio to enhance stability and returns, we propose employing reinforcement learning (RL) to address dynamic decision-making challenges. However, traditional RL methods often struggle to adapt to significant market volatility, primarily by focusing on adjusting existing asset weights. Different from traditional RL methods, the multi-agent reinforcement learning correctable strategy (MAC) developed in this study detects and replaces potentially harmful assets with familiar alternatives, ensuring a resilient response to market crises. Utilizing the multi-agent reinforcement learning model, MAC empowers individual agents to maximize portfolio returns and minimize risk separately. During training, MAC strategically replaces assets to simulate market changes, allowing agents to learn risk-identification through uncertainty estimation. During testing, MAC detects potentially harmful assets and replaces them with more reliable alternatives, enhancing portfolio stability. Experiments conducted on a real-world US Exchange-Traded Fund (ETF) market dataset demonstrate MAC’s superiority over standard RL-based PM methods and other baselines, underscoring its practical efficacy for real-world applications.
- 29 January 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 120 (1) , 11
Open AccessMulti-Agent Reinforcement Learning Correctable Strategy: A Framework with Correctable Strategies for Portfolio Management
Portfolio management (PM) is a broad investment strategy aimed at risk mitigation through diversified financial product investments. Acknowledging the significance of dynamic adjustments after establishing a portfolio to enhance stability and returns, we propose employing reinforcement learning (RL) to address dynamic decision-making challenges. However, traditional RL methods often struggle to adapt to significant market volatility, primarily by focusing on adjusting existing asset weights. Different from traditional RL methods, the multi-agent reinforcement learning correctable strategy (MAC) developed in this study detects and replaces potentially harmful assets with familiar alternatives, ensuring a resilient response to market crises. Utilizing the multi-agent reinforcement learning model, MAC empowers individual agents to maximize portfolio returns and minimize risk separately. During training, MAC strategically replaces assets to simulate market changes, allowing agents to learn risk-identification through uncertainty estimation. During testing, MAC detects potentially harmful assets and replaces them with more reliable alternatives, enhancing portfolio stability. Experiments conducted on a real-world US Exchange-Traded Fund (ETF) market dataset demonstrate MAC’s superiority over standard RL-based PM methods and other baselines, underscoring its practical efficacy for real-world applications.
- Open Access
Extending Automatic Machine Translation Evaluation to Book-Length Documents
Despite Large Language Models (LLMs) demonstrating superior translation performance and long-context capabilities, evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations, token number restrictions in metrics, and rigid sentence boundary requirements. We introduce SEGALE, an evaluation scheme that extends existing automatic metrics to long-document translation by treating documents as continuous text and applying sentence segmentation and alignment methods. Our approach enables previously unattainable document-level evaluation, handling translations of arbitrary length generated with document-level prompts while accounting for under-/over-translations and varied sentence boundaries. Experiments show our scheme significantly outperforms existing long-form document evaluation schemes, while being comparable to evaluations performed with groundtruth sentence alignments. Additionally, we apply our scheme to book-length texts and newly demonstrate that many open-weight LLMs fail to effectively translate documents at their reported maximum context lengths.
Open AccessExtending Automatic Machine Translation Evaluation to Book-Length Documents
Despite Large Language Models (LLMs) demonstrating superior translation performance and long-context capabilities, evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations, token number restrictions in metrics, and rigid sentence boundary requirements. We introduce SEGALE, an evaluation scheme that extends existing automatic metrics to long-document translation by treating documents as continuous text and applying sentence segmentation and alignment methods. Our approach enables previously unattainable document-level evaluation, handling translations of arbitrary length generated with document-level prompts while accounting for under-/over-translations and varied sentence boundaries. Experiments show our scheme significantly outperforms existing long-form document evaluation schemes, while being comparable to evaluations performed with groundtruth sentence alignments. Additionally, we apply our scheme to book-length texts and newly demonstrate that many open-weight LLMs fail to effectively translate documents at their reported maximum context lengths.
- Open Access
NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks
Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini's research mode) highlight potential for structured tasks by autonomous decision-making and task decomposition; however, it remains unclear to what extent the agent-based systems can improve multimodal web data productivity. We study this in the realm of journalism, which requires iterative planning, interpretation, and contextual reasoning from multimodal raw contents to form a well structured news. We introduce NEWSAGENT, a benchmark for evaluating how agents can automatically search available raw contents, select desired information, and edit and rephrase to form a news article by accessing core journalistic functions. Given a writing instruction and firsthand data as how a journalist initiates a news draft, agents are tasked to identify narrative perspectives, issue keyword-based queries, retrieve historical background, and generate complete articles. Unlike typical summarization or retrieval tasks, essential context is not directly available and must be actively discovered, reflecting the information gaps faced in real-world news writing. NEWSAGENT includes 6k human-verified examples derived from real news, with multimodal contents converted to text for broad model compatibility. We evaluate open- and closed-sourced LLMs with commonly-used agentic frameworks on NEWSAGENT, which shows that agents are capable of retrieving relevant facts but struggling with planning and narrative integration. We believe that NEWSAGENT serves a realistic testbed for iterating and evaluating agent capabilities in terms of multimodal web data manipulation to real-world productivity.
Open AccessNEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks
Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini's research mode) highlight potential for structured tasks by autonomous decision-making and task decomposition; however, it remains unclear to what extent the agent-based systems can improve multimodal web data productivity. We study this in the realm of journalism, which requires iterative planning, interpretation, and contextual reasoning from multimodal raw contents to form a well structured news. We introduce NEWSAGENT, a benchmark for evaluating how agents can automatically search available raw contents, select desired information, and edit and rephrase to form a news article by accessing core journalistic functions. Given a writing instruction and firsthand data as how a journalist initiates a news draft, agents are tasked to identify narrative perspectives, issue keyword-based queries, retrieve historical background, and generate complete articles. Unlike typical summarization or retrieval tasks, essential context is not directly available and must be actively discovered, reflecting the information gaps faced in real-world news writing. NEWSAGENT includes 6k human-verified examples derived from real news, with multimodal contents converted to text for broad model compatibility. We evaluate open- and closed-sourced LLMs with commonly-used agentic frameworks on NEWSAGENT, which shows that agents are capable of retrieving relevant facts but struggling with planning and narrative integration. We believe that NEWSAGENT serves a realistic testbed for iterating and evaluating agent capabilities in terms of multimodal web data manipulation to real-world productivity.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2706-2710
Template-Based Financial Report Generation in Agentic and Decomposed Information Retrieval
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2706-2710
Open AccessTemplate-Based Financial Report Generation in Agentic and Decomposed Information Retrieval
- 20 June 2025
- Published by Springer Nature
- p. 434-445
DDOT: A Derivative-Directed Dual-Decoder Ordinary Differential Equation Transformer for Dynamic System Modeling
- 20 June 2025
- Published by Springer Nature
- p. 434-445
DDOT: A Derivative-Directed Dual-Decoder Ordinary Differential Equation Transformer for Dynamic System Modeling
- Open Access
Mixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalanced Regression
Tabular data serve as a fundamental and ubiquitous representation of structured information in numerous real-world applications, e.g., finance and urban planning. In the realm of tabular imbalanced applications, data imbalance has been investigated in classification tasks with insufficient instances in certain labels, causing the model's ineffective generalizability. However, the imbalance issue of tabular regression tasks is underexplored, and yet is critical due to unclear boundaries for continuous labels and simplifying assumptions in existing imbalance regression work, which often rely on known and balanced test distributions. Such assumptions may not hold in practice and can lead to performance degradation. To address these issues, we propose MATI: Mixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalance Regression, featuring two key innovations: (i) the Region-Aware Mixture Expert, which adopts a Gaussian Mixture Model to capture the underlying related regions. The statistical information of each Gaussian component is then used to synthesize and train region-specific experts to capture the unique characteristics of their respective regions. (ii) Test-Time Self-Supervised Expert Aggregation, which dynamically adjusts region expert weights based on test data features to reinforce expert adaptation across varying test distributions. We evaluated MATI on four real-world tabular imbalance regression datasets, including house pricing, bike sharing, and age prediction. To reflect realistic deployment scenarios, we adopted three types of test distributions: a balanced distribution with uniform target frequencies, a normal distribution that follows the training data, and an inverse distribution that emphasizes rare target regions. On average across these three test distributions, MATI achieved a 7.1% improvement in MAE compared to existing methods.
Open AccessMixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalanced Regression
Tabular data serve as a fundamental and ubiquitous representation of structured information in numerous real-world applications, e.g., finance and urban planning. In the realm of tabular imbalanced applications, data imbalance has been investigated in classification tasks with insufficient instances in certain labels, causing the model's ineffective generalizability. However, the imbalance issue of tabular regression tasks is underexplored, and yet is critical due to unclear boundaries for continuous labels and simplifying assumptions in existing imbalance regression work, which often rely on known and balanced test distributions. Such assumptions may not hold in practice and can lead to performance degradation. To address these issues, we propose MATI: Mixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalance Regression, featuring two key innovations: (i) the Region-Aware Mixture Expert, which adopts a Gaussian Mixture Model to capture the underlying related regions. The statistical information of each Gaussian component is then used to synthesize and train region-specific experts to capture the unique characteristics of their respective regions. (ii) Test-Time Self-Supervised Expert Aggregation, which dynamically adjusts region expert weights based on test data features to reinforce expert adaptation across varying test distributions. We evaluated MATI on four real-world tabular imbalance regression datasets, including house pricing, bike sharing, and age prediction. To reflect realistic deployment scenarios, we adopted three types of test distributions: a balanced distribution with uniform target frequencies, a normal distribution that follows the training data, and an inverse distribution that emphasizes rare target regions. On average across these three test distributions, MATI achieved a 7.1% improvement in MAE compared to existing methods.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21536-21544
APAR: Modeling Irregular Target Functions in Tabular Regression via Arithmetic-Aware Pre-Training and Adaptive-Regularized Fine-Tuning
Tabular data are fundamental in common machine learning applications, ranging from finance to genomics and healthcare. This paper focuses on tabular regression tasks, a field where deep learning (DL) methods are not consistently superior to machine learning (ML) models due to the challenges posed by irregular target functions inherent in tabular data, causing sensitive label changes with minor variations from features. To address these issues, we propose a novel Arithmetic-Aware Pre-training and Adaptive-Regularized Fine-tuning framework (APAR), which enables the model to fit irregular target function in tabular data while reducing the negative impact of overfitting. In the pre-training phase, APAR introduces an arithmetic-aware pretext objective to capture intricate sample-wise relationships from the perspective of continuous labels. In the fine-tuning phase, a consistency-based adaptive regularization technique is proposed to self-learn appropriate data augmentation. Extensive experiments across 10 datasets demonstrated that APAR outperforms existing GBDT-, supervised NN-, and pretrain-finetune NN-based methods in RMSE (+9.43% ~ 20.37%), and empirically validated the effects of pre-training tasks, including the study of arithmetic operations.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21536-21544
Open AccessAPAR: Modeling Irregular Target Functions in Tabular Regression via Arithmetic-Aware Pre-Training and Adaptive-Regularized Fine-Tuning
Tabular data are fundamental in common machine learning applications, ranging from finance to genomics and healthcare. This paper focuses on tabular regression tasks, a field where deep learning (DL) methods are not consistently superior to machine learning (ML) models due to the challenges posed by irregular target functions inherent in tabular data, causing sensitive label changes with minor variations from features. To address these issues, we propose a novel Arithmetic-Aware Pre-training and Adaptive-Regularized Fine-tuning framework (APAR), which enables the model to fit irregular target function in tabular data while reducing the negative impact of overfitting. In the pre-training phase, APAR introduces an arithmetic-aware pretext objective to capture intricate sample-wise relationships from the perspective of continuous labels. In the fine-tuning phase, a consistency-based adaptive regularization technique is proposed to self-learn appropriate data augmentation. Extensive experiments across 10 datasets demonstrated that APAR outperforms existing GBDT-, supervised NN-, and pretrain-finetune NN-based methods in RMSE (+9.43% ~ 20.37%), and empirically validated the effects of pre-training tasks, including the study of arithmetic operations.