Ai Magazine最新文献_第3页

AI-driven discovery of feasible 3D printing configurations for metal alloys 人工智能驱动下发现可行的金属合金3D打印配置

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-22 DOI: 10.1002/aaai.70069

Azza Fadhel, Nathaniel W. Zuckschwerdt, Aryan Deshwal, Susmita Bose, Amit Bandyopadhyay, Jana Doppa

{"title":"AI-driven discovery of feasible 3D printing configurations for metal alloys","authors":"Azza Fadhel, Nathaniel W. Zuckschwerdt, Aryan Deshwal, Susmita Bose, Amit Bandyopadhyay, Jana Doppa","doi":"10.1002/aaai.70069","DOIUrl":"https://doi.org/10.1002/aaai.70069","url":null,"abstract":"Configuring additive manufacturing (AM) processes for metal alloys is challenging because printed output quality depends on complex interactions among process parameters such as laser power, scan speed, and feed rate. Conventional trial-and-error approaches are inefficient because experiments are costly and the process parameter space is extremely large. More broadly, this setting reflects a growing class of scientific discovery problems in which experiments are expensive and experimental resources must be allocated intelligently. This paper presents a Bayesian Experimental design for AM (BEAM) methodology that combines principles of AI-driven adaptive experimental design with domain knowledge to accelerate discovery of feasible process configurations. BEAM treats process development as a closed-loop learning problem: a probabilistic surrogate model learns from prior experiments and iteratively recommends promising configurations for laboratory validation. This creates a human-AI collaborative workflow in which domain experts define physical constraints, AI prioritizes experiments, and laboratory feedback improves future recommendations. We deploy BEAM on a directed energy deposition (DED) process to print GRCop-42, a NASA-developed copper alloy that is difficult to process using conventional infrared laser systems because of its low laser absorptivity and high thermal conductivity. Within three months, BEAM discovered multiple defect-free process configurations across laser power levels from 950 to 500W, dramatically reducing time and resource expenditure compared to several months of unsuccessful manual experimentation. By enabling high-quality GRCop-42 fabrication on widely available lower-power infrared laser platforms for the first time, this work demonstrates how AI-guided experimental design can accelerate scientific and engineering discovery in resource-constrained settings.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large scale retrieval for the LinkedIn feed using causal language models 使用因果语言模型对LinkedIn提要进行大规模检索

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-22 DOI: 10.1002/aaai.70078

Sudarshan Srinivasa Ramanujam, Antonio Alonso, Saurabh Kataria, Siddharth Dangi, Akhilesh Gupta, Birjodh Singh Tiwana, Manas Haribhai Somaiya, Luke Simon, David Byrne, Madhu Arun, Sojeong Ha, Sen Zhou, Andrei Akterskii, Zhanglong Liu, Samira Sriram, Zihan Xiong, Zhoutao Pei, Angela Shao, Alex Li, Annie Xiao, Caitlin Kolb, Thomas Kistler, Zach Moore, Hamed Firooz

{"title":"Large scale retrieval for the LinkedIn feed using causal language models","authors":"Sudarshan Srinivasa Ramanujam, Antonio Alonso, Saurabh Kataria, Siddharth Dangi, Akhilesh Gupta, Birjodh Singh Tiwana, Manas Haribhai Somaiya, Luke Simon, David Byrne, Madhu Arun, Sojeong Ha, Sen Zhou, Andrei Akterskii, Zhanglong Liu, Samira Sriram, Zihan Xiong, Zhoutao Pei, Angela Shao, Alex Li, Annie Xiao, Caitlin Kolb, Thomas Kistler, Zach Moore, Hamed Firooz","doi":"10.1002/aaai.70078","DOIUrl":"https://doi.org/10.1002/aaai.70078","url":null,"abstract":"In large-scale recommendation systems like LinkedIn's, the retrieval stage is critical for narrowing billions of potential candidates to a manageable subset for ranking. LinkedIn's feed now serves suggested content based on the topical interests of members, where 2000 candidates are retrieved from several million candidates with a latency budget of a few milliseconds and inbound QPS of several thousand per second. This paper presents a novel retrieval approach that fine tunes a large causal language model (Meta's LLaMA 3) as a dual encoder to generate high quality embeddings for both users (members) and content (items), using only textual input. We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine tuning at LinkedIn scale, and infrastructure for low latency, cost effective online serving. We share our findings on how quantizing numerical features in the prompt enables the information getting encoded in the embedding facilitating greater alignment between the retrieval and ranking layer. The system was evaluated using offline metrics and an online A/B test, which showed substantial improvements in member engagement. We observed significant gains among newer members, who often lack strong network connections, indicating that high-quality suggested content aids retention. This work demonstrates how generative language models can be effectively adapted for real time, high throughput retrieval in industrial applications.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A deployed investigative AI search engine for combating human trafficking at web scale 一个部署的调查人工智能搜索引擎，用于在网络规模上打击人口贩运

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-22 DOI: 10.1002/aaai.70071

Mayank Kejriwal

{"title":"A deployed investigative AI search engine for combating human trafficking at web scale","authors":"Mayank Kejriwal","doi":"10.1002/aaai.70071","DOIUrl":"https://doi.org/10.1002/aaai.70071","url":null,"abstract":"Online human trafficking investigations generate vast amounts of noisy, heterogeneous, and deliberately obfuscated data, making traditional search and analytics tools ineffective for supporting law enforcement. This paper discusses the deployment of the Domain-Specific Insight Graphs (DIG) system, an AI-powered investigative search engine that was operationally used by over 200 U.S. law enforcement agencies for more than five years in the pre-COVID period. The system integrates advanced research conducted over the years in information extraction, knowledge graph construction, and entity-centric search to enable investigators to formulate queries without technical background, aggregate evidence, and uncover latent relationships among entities such as phone numbers, emails, and locations. Beyond technical innovation, the deployment required sustained attention to usability, explainability, and policy compliance, ensuring trust in high-stakes legal contexts. We report measurable benefits in investigative efficiency, case initiation, and prosecutorial support, as well as lessons learned from long-term maintenance and adaptation to evolving online platforms. Since 2020, work conducted in this domain has also had significant policy and advocacy ramifications. The system's generalized design has also allowed it to be prototyped for adjacent illicit domains, including securities fraud and illegal firearm sales, demonstrating the broader applicability of AI-driven investigative tools. We contribute a rare case study of an AI system that has transitioned from research to sustained real-world impact in a socially critical domain.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70071","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human-in-the-loop eider duck counting in Arctic Canada with an open-vocabulary multispecies wildlife detector 用开放词汇的多物种野生动物探测器在加拿大北极进行绒鸭计数

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-20 DOI: 10.1002/aaai.70077

Jayden Hsiao, Aryan Kalia, Zhonghao Zhang, Hudson Sun, Muhammed Patel, David A. Clausi, Lincoln Linlin Xu, Becky Segal, Joel Heath

{"title":"Human-in-the-loop eider duck counting in Arctic Canada with an open-vocabulary multispecies wildlife detector","authors":"Jayden Hsiao, Aryan Kalia, Zhonghao Zhang, Hudson Sun, Muhammed Patel, David A. Clausi, Lincoln Linlin Xu, Becky Segal, Joel Heath","doi":"10.1002/aaai.70077","DOIUrl":"https://doi.org/10.1002/aaai.70077","url":null,"abstract":"Accurate monitoring of eider duck populations in Arctic Canada is essential for understanding ecosystem health and supporting conservation efforts in a rapidly changing climate. Traditional manual counting from aerial imagery is time-consuming, labor-intensive, and prone to observer bias. In this work, we present a human-in-the-loop wildlife counting system that integrates an open-vocabulary multi-species object detector to streamline and enhance the accuracy of eider duck surveys. The system leverages a pretrained open-vocabulary model, enabling the identification of both target and incidental species without retraining, and employs human validation to correct and refine automated detections. This collaborative workflow combines the scalability of machine learning with expert ecological knowledge, reducing annotation effort while maintaining high accuracy. Field validation using aerial imagery from Arctic Canada demonstrates that our approach can significantly accelerate population assessments, improve consistency across surveys, and facilitate adaptive monitoring in remote environments.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reducing alert fatigue through AI ranking: A deployed public health data monitoring system 通过人工智能排名减少警报疲劳：一种部署的公共卫生数据监测系统

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-20 DOI: 10.1002/aaai.70081

Ananya Joshi, Nolan Gormley, Richa Gadgil, Catalina Vajiac, Tina Townes, Roni Rosenfeld, Bryan Wilder

{"title":"Reducing alert fatigue through AI ranking: A deployed public health data monitoring system","authors":"Ananya Joshi, Nolan Gormley, Richa Gadgil, Catalina Vajiac, Tina Townes, Roni Rosenfeld, Bryan Wilder","doi":"10.1002/aaai.70081","DOIUrl":"https://doi.org/10.1002/aaai.70081","url":null,"abstract":"Public health experts need scalable methods to monitor large volumes of health data and identify data points that may indicate significant events, such as outbreaks or data quality issues. Experts then triage and analyze these data points so that they can prevent downstream errors in forecasting or policy. Still, traditional alert-based data monitoring systems, used for decades in public health practice, may return tens of thousands of unhelpful alerts, making relevant events difficult to identify.We introduce a human-in-the-loop AI system for public health data monitoring that uses a ranking-based AI anomaly detection method. This system has since been deployed at a national public health organization under loads of up to 5 million data points daily. A three-month longitudinal deployment evaluation revealed a significant improvement in system goals, including a 54x increase in data reviewer efficiency and increased engagement compared to traditional alert-based methods.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing preferential rate in retail lending with causal inference and domain adaptation 基于因果推理和领域适应的零售贷款优惠利率优化

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-19 DOI: 10.1002/aaai.70079

Jimyung Choi, Yujin Lee, Hyeryeong Oh, Sumin Shin, Jaehyun Kim, Wooyoung Kim, Kee-Eung Kim

{"title":"Optimizing preferential rate in retail lending with causal inference and domain adaptation","authors":"Jimyung Choi, Yujin Lee, Hyeryeong Oh, Sumin Shin, Jaehyun Kim, Wooyoung Kim, Kee-Eung Kim","doi":"10.1002/aaai.70079","DOIUrl":"https://doi.org/10.1002/aaai.70079","url":null,"abstract":"In retail lending, offering preferential interest rates is a core marketing instrument for balancing customer acquisition with portfolio profitability. Accurately predicting the effect of interest-rate discounts for each customer is pivotal for optimizing the discount strategy: offering overly generous discounts erodes margins, while insufficient discounts drive price-sensitive customers to defect. Off-the-shelf machine learning uplift models rarely respect the complex operational constraints of financial business, such as tiered rate grids, regulatory guard-rails, and marketing budget ceilings. We propose an integrated system that fuses causal inference and domain adaptation to produce constraint-aware, customer-specific discount recommendations. To further enhance practitioner adoption, a large language model layer translates model outputs into actionable narratives. Developed in Hyundai Capital Services, the system boosted transaction volume by 13%, demonstrating both technical soundness and material business impact.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70079","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging LLM agents and knowledge models for automated legal reasoning 利用LLM代理和知识模型进行自动法律推理

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-19 DOI: 10.1002/aaai.70076

Vladia Pinheiro, Francisco C. J. Bonfim, Sara Pessoa Silva, Alicia S. Neves, Henrique Santos, João A. Monteiro Neto, Jorge L. B. Araujo, Rilder S. Pires, Ricardo Alexandre Da Silva Costa, Vasco Furtado

{"title":"Leveraging LLM agents and knowledge models for automated legal reasoning","authors":"Vladia Pinheiro, Francisco C. J. Bonfim, Sara Pessoa Silva, Alicia S. Neves, Henrique Santos, João A. Monteiro Neto, Jorge L. B. Araujo, Rilder S. Pires, Ricardo Alexandre Da Silva Costa, Vasco Furtado","doi":"10.1002/aaai.70076","DOIUrl":"https://doi.org/10.1002/aaai.70076","url":null,"abstract":"Delivering judicial decisions demands interpreting complex texts, analyzing evidence, and reasoning through jurisprudence and law. Recent advances in generative artificial intelligence, particularly large language models (LLM), have shown potential to automate parts of this process, but practical benefits in real-world courts remain limited. This paper introduces SARA, an LLM-powered platform deployed in a Brazilian court, which demonstrates significant efficiency and quality gains through the integration of LLM agents with knowledge models on jurisprudential and basic legal concepts. SARA extracts key elements from documents, including claims, requests, and evidence, and generates reasoning grounded in retrieved precedents. The Jur-KG, modeled through an ontology of concepts such as LegalRelation, LegalGrounds, and LegalClaims, enables semantic matching and retrieval of relevant case law. By representing cases according to the Legal Case Ontology for the Brazilian Judicial System, SARA supports traceable reasoning and addresses competence questions to assess coverage, coherence, and justification of AI-generated outputs. Deployment results show measurable improvements in processing time, consistency, and explainability while ensuring compliance with Brazil's National Council of Justice guidelines. Combining LLM-based agents with domain-specific knowledge graphs yields innovative capabilities and proven impact in judicial decision-making.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70076","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NFH-26-03: Data-efficient robot learning for contact-rich manipulation NFH-26-03：用于富接触操作的数据高效机器人学习

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-17 DOI: 10.1002/aaai.70074

Daniel Seita

{"title":"NFH-26-03: Data-efficient robot learning for contact-rich manipulation","authors":"Daniel Seita","doi":"10.1002/aaai.70074","DOIUrl":"https://doi.org/10.1002/aaai.70074","url":null,"abstract":"Robots have the potential to assist people in homes, hospitals, warehouses, and factories, but today's systems still struggle to learn robust manipulation skills from limited data, especially in contact-rich settings involving clutter, deformable objects, dexterous hands, and coordinated multi-arm behaviors. My research aims to make robot learning more data-efficient and physically grounded by combining three complementary directions: synthetic data augmentation, multimodal sensing, and semantic reasoning with foundation models. First, we develop diffusion-based augmentation methods that expand scarce robot demonstration datasets while preserving geometric and contact consistency. Second, we design learning algorithms and robotic platforms that use vision, touch, force, and other sensory signals to reason about complex physical interactions. Third, we leverage and benchmark Vision-Language Models for manipulation, using their semantic knowledge to guide contact-rich planning while identifying their limitations in low-level physical reasoning. Together, these efforts move toward robots that can learn from fewer demonstrations, understand when and how to make contact, and operate more reliably across cluttered and unstructured real-world environments.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scientific design of complex multi-agent systems: A practice modeling approach 复杂多智能体系统的科学设计：一种实践建模方法

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-14 DOI: 10.1002/aaai.70065

William J. Clancey

引用次数: 0

Talking trails: LLM-enhanced spatiotemporal trajectory modeling for E-bike delivery route planning 对话轨迹：基于llm的电动自行车配送路径规划时空轨迹建模

IF 3.5 4区计算机科学

Ai Magazine Pub Date : 2026-08-13 DOI: 10.1002/aaai.70068

Zhao Li, Yangbohan Jiao, Ji Zhang, Buqing Cao

{"title":"Talking trails: LLM-enhanced spatiotemporal trajectory modeling for E-bike delivery route planning","authors":"Zhao Li, Yangbohan Jiao, Ji Zhang, Buqing Cao","doi":"10.1002/aaai.70068","DOIUrl":"https://doi.org/10.1002/aaai.70068","url":null,"abstract":"Electric bicycles (e-bikes) have become the dominant mode of transportation in China's urban instant delivery industry. However, many riders lack the experience to navigate complex traffic networks and diverse road conditions, leading to reduced delivery efficiency. To address this issue, we present Talking Trails, an e-bike delivery route planning system built upon an LLM-enhanced spatiotemporal trajectory model. Trained on millions of real-world delivery trajectories, fused with spatiotemporal and semantic data information, the model achieves a top-5 rider displacement prediction accuracy of 95% and a route optimization rate of 82.1%. In practice, we augment the core planner with an LLM-driven semantic layer that translates high-level user intent into executable tasks, then pair it with a battery-swap module that continuously validates route feasibility so the vehicle never runs out of charge mid-mission. Currently serving tens of thousands of riders, the system is projected to reduce average delivery mileage by 17% and lower annual carbon emissions by 3978 tons. Overall, Talking Trails significantly improves delivery efficiency, offering a scalable and sustainable solution for instant delivery operations.","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"47 3","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.70068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148719248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0