为概率推理开发高效的精确与近似算法是人工智能研究的长期目标。尽管在处理纯离散或纯连续领域方面已取得实质性进展，但将已开发的解决方案用于处理以离散变量、连续变量及其关系为特征的混合领域却极为困难。加权模型积分（Weighted Model Integration, WMI）近年来作为一种用于混合领域概率推理的统一形式化方法而出现。尽管近期已有大量工作，但让WMI算法能够随混合问题的复杂度而扩展仍然是一项挑战。在本文中，我们指出了现有最先进解决方案的一些重大局限，并开发了一种算法，该算法将基于SMT的枚举（一种形式验证中的高效技术）与对问题结构的有效编码相结合。这使得我们的算法能够避免生成冗余模型，从而大幅节省计算开销。此外，我们展示了基于SMT的方法如何能够无缝地处理不同的积分技术，包括精确方法和近似方法，从而显著扩展了WMI技术能够处理的问题集合。在合成数据集和真实世界数据集上的广泛实验评估证实了所提解决方案相对于现有替代方案的显著优势。该技术的应用潜力还在一个旨在验证概率程序公平性的原型任务上得到了进一步展示。
英文摘要：
The development of efficient exact and approximate algorithms for probabilistic inference is a long-standing goal of artificial intelligence research. Whereas substantial progress has been made in dealing with purely discrete or purely continuous domains, adapting the developed solutions to tackle hybrid domains, characterised by discrete and continuous variables and their relationships, is highly non-trivial. Weighted Model Integration (WMI) recently emerged as a unifying formalism for probabilistic inference in hybrid domains. Despite a considerable amount of recent work, allowing WMI algorithms to scale with the complexity of the hybrid problem is still a challenge. In this paper we highlight some substantial limitations of existing state-of-the-art solutions, and develop an algorithm that combines SMT-based enumeration, an efficient technique in formal verification, with an effective encoding of the problem structure. This allows our algorithm to avoid generating redundant models, resulting in drastic computational savings. Additionally, we show how SMT-based approaches can seamlessly deal with different integration techniques, both exact and approximate, significantly expanding the set of problems that can be tackled by WMI technology. An extensive experimental evaluation on both synthetic and real-world datasets confirms the substantial advantage of the proposed solution over existing alternatives. The application potential of this technology is further showcased on a prototypical task aimed at verifying the fairness of probabilistic programs.
SMT-based Weighted Model Integration with Structure Awareness
University of Trento（特伦托大学）；KU Leuven（鲁汶大学）
加权模型集成（Weighted Model Integration，简称WMO）是一种流行的形式主义，旨在统一混合域中的概率推理方法，涉及逻辑和代数约束。尽管最近有大量的工作，但允许并行算法随着混合问题的复杂性而扩展仍然是一个挑战。在本文中，我们突出了一些现有的国家的最先进的解决方案的实质性限制，并开发了一种算法，结合SMT为基础的枚举，一种有效的技术，在形式化验证，与有效的编码的问题结构。这使得我们的算法可以避免生成冗余模型，从而节省大量的计算。对合成和真实世界数据集的广泛实验评估证实了所提出的解决方案优于现有的替代方案。
Enhancing Temporal Awareness in LLMs for Temporal Point Processes
School of Computer Science and Technology, Tongji University, Shanghai 201804, China（计算机科学与技术学院，同济大学）；College of Cyber Security, Jinan University, Guangzhou 510632, China（网络安全学院，暨南大学）；Department of Computer Science, University of Illinois Chicago, Chicago, USA（计算机科学系，伊利诺伊大学芝加哥分校）
Enhancing Deep Learning Based Structured Illumination Microscopy Reconstruction with Light Field Awareness
University of Science and Technology of China（中国科学技术大学）；CAS Center For Excellence in Quantum Information and Quantum Physics（中科院量子信息与量子科技创新研究院）；Hefei National Laboratory（合肥国家实验室）
Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning
Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Huawei Noah’s Ark Lab（华为诺亚实验室）；College of AI, Tsinghua University（清华大学人工智能学院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness
Autonomous Intelligent Systems group, Computer Science Institute VI – Intelligent Systems and Robotics – and the Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Germany（自主智能系统组，计算机科学研究所VI——智能系统与机器人——以及机器人中心和拉玛尔人工智能与机器学习研究所，波恩大学，德国）
Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling
X-LANCE Lab, School of Computer Science MoE Key Lab of Artificial Intelligence, SJTU AI Institute Shanghai Jiao Tong University, Shanghai, China（X-LANCE实验室，计算机科学学院，人工智能关键实验室，上海交通大学人工智能研究院，上海，中国）；Jiangsu Key Lab of Language Computing, Suzhou, China（语言计算重点实验室，苏州，中国）；AISpeech Co., Ltd., Suzhou, China（AISpeech公司，苏州，中国）；Center for Artificial Intelligence Research (CAiRE) Hong Kong University of Science and Technology, Hong Kong, China（人工智能研究中心（CAiRE）香港科技大学，香港，中国）；Suzhou Laboratory, Suzhou, China（苏州实验室，苏州，中国）
