Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Shirui Pan, Qingsong Wen
Diffusion models have been widely used in time series and spatio-temporal data, enhancing generative, inferential, and downstream capabilities. These models are applied across diverse fields such as healthcare, recommendation, climate, energy, audio, and traffic. By separating applications for time series and spatio-temporal data, we offer a structured perspective on model category, task type, data modality, and practical application domain. This study aims to provide a solid foundation for researchers and practitioners, inspiring future innovations that tackle traditional challenges and foster novel solutions in diffusion model-based data mining tasks and applications. For more detailed information, we have open-sourced a repository.
{"title":"A Survey on Diffusion Models for Time Series and Spatio-Temporal Data","authors":"Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Shirui Pan, Qingsong Wen","doi":"10.1145/3783986","DOIUrl":"https://doi.org/10.1145/3783986","url":null,"abstract":"Diffusion models have been widely used in time series and spatio-temporal data, enhancing generative, inferential, and downstream capabilities. These models are applied across diverse fields such as healthcare, recommendation, climate, energy, audio, and traffic. By separating applications for time series and spatio-temporal data, we offer a structured perspective on model category, task type, data modality, and practical application domain. This study aims to provide a solid foundation for researchers and practitioners, inspiring future innovations that tackle traditional challenges and foster novel solutions in diffusion model-based data mining tasks and applications. For more detailed information, we have open-sourced a repository.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"110 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145711161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weibang Dai, Xiaogang Chen, Houpeng Chen, Sannian Song, Shunfen Li, Tao Hong, Zhitang Song
For decades, memory-based computation has been overshadowed by processor-centric paradigms. However, memory-based computation offers distinct advantages, including high-speed operation and energy efficiency. As a representative and powerful type of memory-based computation, lookup table (LUT)-based computing has seen a resurgence in interest. Recent advancements in memory technologies, particularly cost reduction in memories and the rise of emerging non-volatile memories (NVMs), have spurred widespread adoption of LUT-based approaches. In this paper, we first trace the historical evolution of LUT-based computation, then systematically analyze its modern applications across two domains: (1) software implementations, including LUT-based function evaluation and LUT-based neural networks; and (2) hardware architectures, such as LUT in FPGA and LUT-based processing-in-memory (PIM) systems. Finally, we discuss how NVMs could unlock new opportunities for next-generation LUT-based computing.
{"title":"Lookup Table-based Computing: A Survey from Software Implementations to Hardware Architectures","authors":"Weibang Dai, Xiaogang Chen, Houpeng Chen, Sannian Song, Shunfen Li, Tao Hong, Zhitang Song","doi":"10.1145/3779417","DOIUrl":"https://doi.org/10.1145/3779417","url":null,"abstract":"For decades, memory-based computation has been overshadowed by processor-centric paradigms. However, memory-based computation offers distinct advantages, including high-speed operation and energy efficiency. As a representative and powerful type of memory-based computation, lookup table (LUT)-based computing has seen a resurgence in interest. Recent advancements in memory technologies, particularly cost reduction in memories and the rise of emerging non-volatile memories (NVMs), have spurred widespread adoption of LUT-based approaches. In this paper, we first trace the historical evolution of LUT-based computation, then systematically analyze its modern applications across two domains: (1) software implementations, including LUT-based function evaluation and LUT-based neural networks; and (2) hardware architectures, such as LUT in FPGA and LUT-based processing-in-memory (PIM) systems. Finally, we discuss how NVMs could unlock new opportunities for next-generation LUT-based computing.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"115 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jelena Smiljanić, Christopher Blöcker, Anton Holmgren, Daniel Edler, Magnus Neuman, Martin Rosvall
Real-world networks have a complex topology comprising many elements often structured into communities. Revealing these communities helps researchers uncover the organizational and functional structure of the system that the network represents. However, detecting community structures in complex networks requires selecting a community detection method among a multitude of alternatives with different network representations, community interpretations, and underlying mechanisms. This tutorial focuses on a popular community detection method called the map equation and its search algorithm Infomap. The map equation framework for community detection describes communities by analyzing dynamic processes on the network. Thanks to its flexibility, the map equation provides extensions that can incorporate various assumptions about network structure and dynamics. To help decide if the map equation is a suitable community detection method for a given complex system and problem at hand – and which variant to choose – we review the map equation’s theoretical framework and guide users in applying the map equation to various research problems.
{"title":"Community Detection with the Map Equation and Infomap: Theory and Applications","authors":"Jelena Smiljanić, Christopher Blöcker, Anton Holmgren, Daniel Edler, Magnus Neuman, Martin Rosvall","doi":"10.1145/3779648","DOIUrl":"https://doi.org/10.1145/3779648","url":null,"abstract":"Real-world networks have a complex topology comprising many elements often structured into communities. Revealing these communities helps researchers uncover the organizational and functional structure of the system that the network represents. However, detecting community structures in complex networks requires selecting a community detection method among a multitude of alternatives with different network representations, community interpretations, and underlying mechanisms. This tutorial focuses on a popular community detection method called the map equation and its search algorithm Infomap. The map equation framework for community detection describes communities by analyzing dynamic processes on the network. Thanks to its flexibility, the map equation provides extensions that can incorporate various assumptions about network structure and dynamics. To help decide if the map equation is a suitable community detection method for a given complex system and problem at hand – and which variant to choose – we review the map equation’s theoretical framework and guide users in applying the map equation to various research problems.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"34 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ignacio Marco-Pérez, Beatriz Pérez, Angel Luis Rubio Garcia, María A. Zapata
Today, our data is not only stored on personal computers, but is managed by many devices, from cell phones or watches to smart TVs, and stored in remote repositories (usually referred to as “the cloud”). In this new context, defining what exactly “data deletion” is becomes a challenge, especially considering the many different scenarios in which it is becoming more increasingly important. This is the case, for example, of the “right to be forgotten” established by regulations such as the European General Data Protection Regulation (GDPR) or the deletion of data used as a source to feed machine learning processes, the long-term effects of which are very difficult to estimate. This work reviews the various terminology used when dealing with data deletion and analyzes the different fields and technologies to which it is related. We conclude by offering a structured discussion of key takeaways, lessons learned, and future research directions.
{"title":"The Many Faces of Data Deletion: On the Significance and Implications of Deleting Data","authors":"Ignacio Marco-Pérez, Beatriz Pérez, Angel Luis Rubio Garcia, María A. Zapata","doi":"10.1145/3779299","DOIUrl":"https://doi.org/10.1145/3779299","url":null,"abstract":"Today, our data is not only stored on personal computers, but is managed by many devices, from cell phones or watches to smart TVs, and stored in remote repositories (usually referred to as “the cloud”). In this new context, defining what exactly “data deletion” is becomes a challenge, especially considering the many different scenarios in which it is becoming more increasingly important. This is the case, for example, of the “right to be forgotten” established by regulations such as the European General Data Protection Regulation (GDPR) or the deletion of data used as a source to feed machine learning processes, the long-term effects of which are very difficult to estimate. This work reviews the various terminology used when dealing with data deletion and analyzes the different fields and technologies to which it is related. We conclude by offering a structured discussion of key takeaways, lessons learned, and future research directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"10 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peigen Ye, Huali Ren, Zhengdao Li, Anli Yan, Hongyang Yan, Shaowei Wang, Jin Li
State-of-the-art watermarking and fingerprinting techniques for Large Language Models (LLMs) are explored, with our analysis spanning a wide array of methodologies designed to protect the intellectual property of LLMs. The review of watermarking techniques is based on embedding watermarks during the training, logits generation, and token sampling phases. Meanwhile, we investigate the application of watermarking technology in multimodal LLMs and potential attacks on watermarks. Moreover, our examination of fingerprinting techniques revealed the ingenuity behind methods used to identify LLMs. We discussed the development of fingerprints based on model behavior and using deep learning models to learn thresholds for fingerprint comparison. Our survey has underscored the importance of advancing security measures for LLMs, especially in light of the increasing sophistication of adversarial attacks. As LLMs continue to play a pivotal role in advancing AI technologies, developing and refining security measures that safeguard their intellectual property and ensure their ethical deployment is imperative.
{"title":"Securing Large Language Models: A Survey of Watermarking and Fingerprinting Techniques","authors":"Peigen Ye, Huali Ren, Zhengdao Li, Anli Yan, Hongyang Yan, Shaowei Wang, Jin Li","doi":"10.1145/3773028","DOIUrl":"https://doi.org/10.1145/3773028","url":null,"abstract":"State-of-the-art watermarking and fingerprinting techniques for Large Language Models (LLMs) are explored, with our analysis spanning a wide array of methodologies designed to protect the intellectual property of LLMs. The review of watermarking techniques is based on embedding watermarks during the training, logits generation, and token sampling phases. Meanwhile, we investigate the application of watermarking technology in multimodal LLMs and potential attacks on watermarks. Moreover, our examination of fingerprinting techniques revealed the ingenuity behind methods used to identify LLMs. We discussed the development of fingerprints based on model behavior and using deep learning models to learn thresholds for fingerprint comparison. Our survey has underscored the importance of advancing security measures for LLMs, especially in light of the increasing sophistication of adversarial attacks. As LLMs continue to play a pivotal role in advancing AI technologies, developing and refining security measures that safeguard their intellectual property and ensure their ethical deployment is imperative.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"250 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rongxin Zhu, Lei Sheng, Kaitao Wu, Azzedine Boukerche, Libo Long, Qiuling Yang
The growing demand for marine exploration, environmental monitoring, and autonomous underwater operations has elevated the role of underwater image processing in both research and practical applications. However, the acquisition and transmission of underwater visual data are fundamentally constrained by the harsh aquatic environment, where factors such as limited bandwidth, strong light scattering, color distortion, and complex noise severely degrade image quality and restrict data throughput. These challenges not only hinder real-time perception and decision-making but also affect the efficiency of data-driven tasks such as mapping, object recognition, and navigation. To address these issues, a broad spectrum of underwater image processing methods has emerged, aiming to enhance visual clarity, compress data for efficient transmission, restore degraded signals, and enable accurate scene understanding. This survey provides a structured and comprehensive review of existing techniques, categorizing them into four core domains: image enhancement, image restoration, image compression and segmentation, and image classification. Representative methods within each domain are critically analyzed in terms of their underlying principles, computational complexity, and applicability across diverse underwater scenarios. Furthermore, the survey highlights emerging trends including deep learning-based approaches, cross-modal information fusion, and resource-efficient designs, offering insights for future development in underwater visual computing and communication systems.
{"title":"Toward Efficient Underwater Visual Perception through Image Enhancement, Compression, and Understanding","authors":"Rongxin Zhu, Lei Sheng, Kaitao Wu, Azzedine Boukerche, Libo Long, Qiuling Yang","doi":"10.1145/3779223","DOIUrl":"https://doi.org/10.1145/3779223","url":null,"abstract":"The growing demand for marine exploration, environmental monitoring, and autonomous underwater operations has elevated the role of underwater image processing in both research and practical applications. However, the acquisition and transmission of underwater visual data are fundamentally constrained by the harsh aquatic environment, where factors such as limited bandwidth, strong light scattering, color distortion, and complex noise severely degrade image quality and restrict data throughput. These challenges not only hinder real-time perception and decision-making but also affect the efficiency of data-driven tasks such as mapping, object recognition, and navigation. To address these issues, a broad spectrum of underwater image processing methods has emerged, aiming to enhance visual clarity, compress data for efficient transmission, restore degraded signals, and enable accurate scene understanding. This survey provides a structured and comprehensive review of existing techniques, categorizing them into four core domains: image enhancement, image restoration, image compression and segmentation, and image classification. Representative methods within each domain are critically analyzed in terms of their underlying principles, computational complexity, and applicability across diverse underwater scenarios. Furthermore, the survey highlights emerging trends including deep learning-based approaches, cross-modal information fusion, and resource-efficient designs, offering insights for future development in underwater visual computing and communication systems.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"130 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145657753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Digital Twins (DT) paradigm has emerged as a powerful tool for simulating and analyzing complex systems in various domains. A DT is a virtual representation of a real-world object(s) whose goal is to accurately emulate real systems, optimize processes, minimize synchronization delays, cut down on overhead, and automate decision-making. DT technology is moving at a faster than expected pace with advances in Artificial Intelligence (AI), Internet of Things (IoT), Distributed Computing, and 5/6G. Being a highly beneficial technology, DT still faces issues of - (1) limited adaptability, (2) incomplete model representation, (3) suboptimal decision making, (4) limited generalization, and (5) scalability and computational efficiency. Reinforcement Learning (RL) offers unsupervised decision-making and intelligence, which can be immensely beneficial in addressing the current challenges faced by DT. This study offers a thorough analysis of the DT paradigm from the standpoint of RL. The survey compares and contrasts existing reinforcement learning-based Digital Twin frameworks, assessing their advantages and disadvantages. Moreover, discussions of approaches highlighting the trade-offs between simulation fidelity and computing complexity is also studied. Additionally, a thorough understanding of the Digital Twins paradigm from a reinforcement learning perspective, is presented as a helpful resource for academics and industry professionals in the field. Finally, future research directions in this developing field at the nexus of digital modeling, simulation, and artificial intelligence is discussed.
{"title":"Digital Twins Paradigm: A Systematic Review from the Reinforcement Learning Perspective","authors":"Shahmir Khan Mohammed, Shakti Singh, Rabeb Mizouni, Hadi Otrok, Ernesto Damiani","doi":"10.1145/3777367","DOIUrl":"https://doi.org/10.1145/3777367","url":null,"abstract":"The Digital Twins (DT) paradigm has emerged as a powerful tool for simulating and analyzing complex systems in various domains. A DT is a virtual representation of a real-world object(s) whose goal is to accurately emulate real systems, optimize processes, minimize synchronization delays, cut down on overhead, and automate decision-making. DT technology is moving at a faster than expected pace with advances in Artificial Intelligence (AI), Internet of Things (IoT), Distributed Computing, and 5/6G. Being a highly beneficial technology, DT still faces issues of - (1) limited adaptability, (2) incomplete model representation, (3) suboptimal decision making, (4) limited generalization, and (5) scalability and computational efficiency. Reinforcement Learning (RL) offers unsupervised decision-making and intelligence, which can be immensely beneficial in addressing the current challenges faced by DT. This study offers a thorough analysis of the DT paradigm from the standpoint of RL. The survey compares and contrasts existing reinforcement learning-based Digital Twin frameworks, assessing their advantages and disadvantages. Moreover, discussions of approaches highlighting the trade-offs between simulation fidelity and computing complexity is also studied. Additionally, a thorough understanding of the Digital Twins paradigm from a reinforcement learning perspective, is presented as a helpful resource for academics and industry professionals in the field. Finally, future research directions in this developing field at the nexus of digital modeling, simulation, and artificial intelligence is discussed.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"93 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145651429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Inga Miadowicz, Daniel Maldonado Quinto, Michael Felderer
Alongside the vision of autonomous systems, similar system concepts are being discussed in the research fields of highly automated, intelligent, adaptive, autonomic, and organic systems. Although these types of system are studied in scattered research fields that consider them as distinct system classes, they share similar characteristics and are interrelated to some extent. Experts in various fields present a very heterogeneous view on the intersection of autonomous and comparable system concepts, for example, as interchangeable, distinct, or complementary research approaches. Therefore, this study performs a systematic literature review based on more than 300 articles to investigate the intersection of the system classes, emphasizing their similarities, differences, and relationships from the current state of the art.
{"title":"A Systematic Literature Review on the Intersection of Self-X System Classes","authors":"Inga Miadowicz, Daniel Maldonado Quinto, Michael Felderer","doi":"10.1145/3778859","DOIUrl":"https://doi.org/10.1145/3778859","url":null,"abstract":"Alongside the vision of autonomous systems, similar system concepts are being discussed in the research fields of highly automated, intelligent, adaptive, autonomic, and organic systems. Although these types of system are studied in scattered research fields that consider them as distinct system classes, they share similar characteristics and are interrelated to some extent. Experts in various fields present a very heterogeneous view on the intersection of autonomous and comparable system concepts, for example, as interchangeable, distinct, or complementary research approaches. Therefore, this study performs a systematic literature review based on more than 300 articles to investigate the intersection of the system classes, emphasizing their similarities, differences, and relationships from the current state of the art.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"14 10 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145609212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ping Wang, Shishir Nagaraja, Aurélien Bourquard, Haichang Gao, Jeff Yan
Acoustic side channels (ASCs) have been discovered for several decades, highlighting the tangible security risks posed by unintended sound emissions from computing and electronic systems. Their existence has drawn considerable attention from researchers, driving rapid progress in both attack methodologies and defense mechanisms across a wide range of scenarios. In this paper, we provide a state-of-the-art analysis of ASCs, covering all the significant academic research in the area. First, we clarify existing ambiguities and conceptual confusion, proposing a clear definition of ASC. Second, we analyse the characteristics of known ASCs, discuss their security implications, and propose the first taxonomy. Next, we summarise attack techniques, discuss countermeasures, and identify areas for future research. We also link side channels and inverse problems, two fields that appear to be completely isolated from each other but have deep connections.
{"title":"SoK: Acoustic Side Channels","authors":"Ping Wang, Shishir Nagaraja, Aurélien Bourquard, Haichang Gao, Jeff Yan","doi":"10.1145/3778350","DOIUrl":"https://doi.org/10.1145/3778350","url":null,"abstract":"Acoustic side channels (ASCs) have been discovered for several decades, highlighting the tangible security risks posed by unintended sound emissions from computing and electronic systems. Their existence has drawn considerable attention from researchers, driving rapid progress in both attack methodologies and defense mechanisms across a wide range of scenarios. In this paper, we provide a state-of-the-art analysis of ASCs, covering all the significant academic research in the area. First, we clarify existing ambiguities and conceptual confusion, proposing a clear definition of ASC. Second, we analyse the characteristics of known ASCs, discuss their security implications, and propose the first taxonomy. Next, we summarise attack techniques, discuss countermeasures, and identify areas for future research. We also link side channels and inverse problems, two fields that appear to be completely isolated from each other but have deep connections.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"17 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145599034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
AI systems are not only becoming better in solving complex reasoning challenges, but also in performing creative tasks. One of the creative tasks where AI systems still struggle to achieve human performance, however, is humor processing, for which mixed results have been reported. Therefore, the goal of this survey is to categorize recent research in computational humor modeling in order to identify current trends, advancements, and remaining gaps. The scope of this work is broader than previous survey papers, as we tackle not only text-based models, but also multimodal models, and discuss a variety of detection and generation tasks.
{"title":"Computational Humor Modeling: A Survey on the State of the Art","authors":"Jens Lemmens, Victor De Marez","doi":"10.1145/3778357","DOIUrl":"https://doi.org/10.1145/3778357","url":null,"abstract":"AI systems are not only becoming better in solving complex reasoning challenges, but also in performing creative tasks. One of the creative tasks where AI systems still struggle to achieve human performance, however, is humor processing, for which mixed results have been reported. Therefore, the goal of this survey is to categorize recent research in computational humor modeling in order to identify current trends, advancements, and remaining gaps. The scope of this work is broader than previous survey papers, as we tackle not only text-based models, but also multimodal models, and discuss a variety of detection and generation tasks.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"89 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145599033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：