• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    宏

    宏利金融股份有限公司

    Manulife
    企业EST. 1887
    27论文总数
    287引用总数

    宁波宏利集团有限公司,是专业生产出口针织服装和花色针织布的大型企业。至今有20多年的历史。是省内重要的针织品出口基地。拥有自营进出口经营权,2002年7月一次性通过质量体系认证。

    论文量&引用量时间轴

    机构学者

    论文(27)

    年份
    起
    –
    止
    排序
    1When Synthetic Data Hurts: on Catastrophic Forgetting in Skill Retrieval for LLM Agents
    Syed Shariyar Murtaza,Yifan Nie, Utkarsh Soni, Eugene Wen, Arvid Frydenlund

    LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present a production skill router over 34,396 skills and a large-scale study of skill retrieval using limited real supervision and synthetic data. We found that the synthetic-data fine-tuning improves in-distribution retrieval but it causes catastrophic forgetting on real and out-of-distribution (OOD) data. We evaluate several forgetting mitigation fine-tuning approaches inspired by continual learning, including embedding-anchor regularization, Learning without Forgetting (LwF), Elastic Weight Consolidation (EWC), and L2-initialization. The results show that these approaches not only retain the performance on OOD skills retrieval but also improve the retrieval on synthetic in-distribution skills by 13.98% for 0.6B Qwen retriever and reranker. Our results provide a practical benchmark and a robust fine-tuning recipe for scarce, multi-positive supervision.

    2026Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing Industry Trac...(2026)引用:3
    引用
    AI阅读
    加入学术空间
    2Understanding Multi-Structured Documents Via LLMs’
    Shivani Upadhyay, Messiah Ataey, Syed Shariyar Murtaza, Yifan Nie, Anirudh Aggarwal,Jimmy Lin

    Complexly structured data present in documents and web content pose significant challenges for accurate MLLM reasoning. Although MLLMs have advanced substantially, they continue to struggle with intricate data formats such as nested tables and multi-dimensional charts, often leading to hallucinations. This paper explores the capabilities of LLMs and MLLMs in understanding and answering questions from complex data found in PDF documents by leveraging a pre-processing pipeline consisting of industrial and open-source tools. Our results showcase that incorporating RAG and pre-processing tools enables MLLMs to achieve approximately 5 https://github.com/manulife-ai/financialqa .

    2026Advances in Information Retrieval(2026)
    引用
    AI阅读
    加入学术空间
    3A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems
    William Loh, Sajib Kumer Sinha, Ankur Agarwal,Pascal Poupart

    Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functions, and (3) a generalization of correlated bandits where reward distributions change over time but the degree of correlation maintains. This formulation lends itself to a wider set of applications such as recommendation tasks. To solve this problem, we introduce *conditionally coupled contextual* ($C_3$) Thompson sampling for Bernoulli bandits. It combines an improved Nadaraya-Watson estimator on an embedding space with Thompson sampling that allows online learning without retraining. Empirical results show that $C_3$ outperforms the next best algorithm by 5.7% lower average cumulative regret on four OpenML tabular datasets as well as demonstrating a 12.4% click lift on Microsoft News Dataset (MIND) compared to other algorithms.

    TMLR
    引用
    AI阅读
    加入学术空间
    4Risk-Based Governance for Autonomous Decision Systems
    Naresh Alapati, Ramachander rao Thallada, Koteswararao Nallabothu

    Artificial intelligence-based autonomous decision systems are being implemented in the fields of finance, healthcare, transportation, and governance of the people. They are used to improve the accuracy, speed, and scalability of decisions through processing high volumes of data and autonomously generating responses without requiring human intervention. Nevertheless, the adoption of autonomous decision systems is rapid, and it presents new governance issues in transparency, accountability, algorithms, as well as operational risks. The old models of governance still depend on manual supervision and fixed policy enforcement that cannot be used to deal with the dynamic AI-driven environments. The following paper proposes a risk-based governing framework that is aimed at providing responsible and trustworthy functioning of autonomous decision systems. The suggested framework incorporates risk identification, risk assessment, governance policy enforcement, and on-going monitoring mechanisms to handle operational and ethical risks. The framework enables organizations to implement the right governance controls by categorizing autonomous systems according to the level of risk and still providing flexibility in operations. Moreover, the architecture has elements of explainability and compliance monitoring to reinforce transparency and accountability. The research emphasizes the role of risk-based governance in allowing organizations to reduce the risks associated with decisions, enhance the adherence to regulations, and increase trust in AI-based decision systems. The suggested framework offers an organized method of governance that facilitates innovation and sustainable use of autonomous decision technologies.

    2026Journal of Business and Management Studies(2026)
    引用
    AI阅读
    加入学术空间
    5Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
    Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti, Utkarsh Soni,Yifan Nie, Eugene Wen,Yuntian Deng

    Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication. This design allows optimizers to improve multi-agent behavior without exposing the routing or formatting interface to prompt drift. Across synthetic reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100

    2026Findings of the Association for Computational Linguistics EMNLP 2026(2026)
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 27 篇论文

    合作机构(12)

    约克大学合作论文 5
    滑铁卢大学合作论文 5
    Lowe's合作论文 5
    沃尔玛合作论文 5
    麦克马斯特大学合作论文 1
    新加坡国立大学合作论文 1
    东京电机大学合作论文 1
    南洋理工大学合作论文 1
    Grand River Hospital合作论文 1
    Bogor Agricultural University合作论文 1

    机构统计