Knowledge graphs and vector space models are robust knowledge representation techniques with individual strengths and weaknesses. Vector space models excel at determining similarity between concepts, but are severely constrained when evaluating complex dependency relations and other logic-based operations that are a strength of knowledge graphs. We describe the VKG structure that helps unify knowledge graphs and vector representation of entities, and enables powerful inference methods and search capabilities that combine their complementary strengths. We analogize this to thinking `fast' in vector space along with thinking 'slow' and `deeply' by reasoning over the knowledge graph. We have created a query processing engine that takes complex queries and decomposes them into subqueries optimized to run on the respective knowledge graph or vector view of a VKG. We show that the VKG structure can process specific queries that are not efficiently handled by vector spaces or knowledge graphs alone. We also demonstrate and evaluate the VKG structure and the query processing engine by developing a system called Cyber-All-Intel for knowledge extraction, representation and querying in an end-to-end pipeline grounded in the cybersecurity informatics domain.
MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Czech Technical University in Prague（布拉格捷克理工大学）；University of Innsbruck（因斯布鲁克大学）
We describe several additions to the ENIGMA system that guides clause selection in the E automated theorem prover. First, we significantly speed up its neural guidance by adding server-based GPU evaluation. The second addition is motivated by fast weight-based rejection filters that are currently used in systems like E and Prover9. Such systems can be made more intelligent by instead training fast versions of ENIGMA that implement more intelligent pre-filtering. This results in combinations of trainable fast and slow thinking that improves over both the fast-only and slow-only methods. The thi…
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学人工智能学院）；Beijing Key Laboratory of Research on Large Models（北京大型模型研究关键实验室）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心）；College of Artificial Intelligence, Tianjin University of Science（天津科技大学人工智能学院）
IBM；University of Udine（乌迪内大学）；European University Institute（欧洲大学学院）；Tulane University（杜兰大学）；Universty of South Carolina（南卡罗来纳大学）
This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research commun…
Union College（联合学院）；IBM Research（IBM研究院）；University of Udine（乌迪内大学）；University of Brescia（布雷西亚大学）；Tulane University（杜兰大学）；University of West Florida（西佛罗里达大学）；Univ. of South Carolina（南卡罗来纳大学）；Institute for Human and Machine Cognition（人机认知研究所）
Current AI systems lack several important human capabilities, such as adaptability, generalizability, self-control, consistency, common sense, and causal reasoning. We believe that existing cognitive theories of human decision making, such as the thinking fast and slow theory, can provide insights on how to advance AI systems towards some of these capabilities. In this paper, we propose a general architecture that is based on fast/slow solvers and a metacognitive component. We then present experimental results on the behavior of an instance of this architecture, for AI systems that make decisi…
Union College（联合学院）；IBM Research（IBM研究院）；Univ. Udine（乌迪内大学）；EUI（欧洲大学学院）；Tulane Univ.（杜兰大学）；USC（南加利福尼亚大学）；IHMC（人类与机器认知研究所）
AI systems have seen dramatic advancement in recent years, bringing many applications that pervade our everyday life. However, we are still mostly seeing instances of narrow AI: many of these recent developments are typically focused on a very limited set of competencies and goals, e.g., image interpretation, natural language processing, classification, prediction, and many others. Moreover, while these successes can be accredited to improved algorithms and techniques, they are also tightly linked to the availability of huge datasets and computational power. State-of-the-art AI still lacks man…
International Institute of Information Technology Bangalore（班加罗尔国际信息技术学院）
The "Thinking, Fast and Slow" paradigm of Kahneman proposes that we use two different styles of thinking -- a fast and intuitive System 1 for certain tasks, along with a slower but more analytical System 2 for others. While the idea of using this two-system style of thinking is gaining popularity in AI and robotics, our work considers how to interleave the two styles of decision-making, i.e., how System 1 and System 2 should be used together. For this, we propose a novel and general framework which includes a new System 0 to oversee Systems 1 and 2. At every point when a decision needs to be m…
Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference
Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；Shenzhen International Quantum Academy（深圳国际量子研究院）；Hefei National Laboratory（合肥国家实验室）
Cornell University（康奈尔大学）；California Institute of Technology（加州理工学院）
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic-gradient-based neural network optimization. We illustrate the power of DRNets on de-mixing overlapping hand-written Sudokus (Multi-MNIST-Sudoku) and on a substantially more complex task in scientific discovery that concerns inferring crystal structures of materials from X-ray di…
Pratt School of Engineering（普拉特工程学院）；Duke University（杜克大学）；School of Computer Science（计算机科学学院）；Northeast Electric Power University（东北电力大学）；Department of Information and Communication Engineering（信息与通信工程系）；Tongji University（同济大学）；School of Computer Science and Technology（计算机科学与技术学院）；School of International Education（国际教育学院）；Beijing University of Chemical Technology（北京化工大学）；East China Normal University（华东师范大学）；Information Hub（信息枢纽）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Chinese Academy of Science（中国科学院）
Union College（联合学院）；University of Parma（帕尔马大学）；IBM Research（IBM研究院）；University of Brescia（布雷西亚大学）；Tulane University（杜兰大学）；Institute for Human and Machine Cognition（人类与机器认知研究所）
AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；ETH Zurich（苏黎世联邦理工学院）；Hong Kong University of Science and Technology（香港科技大学）；University of Hong Kong（香港大学）；Noah’s Ark Lab（诺亚实验室）；Yinwang Intelligent Technology Co., Ltd.（亿纬智能科技有限公司）
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Southern California（南加州大学）；University of Washington（华盛顿大学）；Tsinghua University（清华大学）；Paradigm Inc.（第四范式公司）；University of California, San Diego（加州大学圣地亚哥分校）；MosaicML（MosaicML公司）
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
University of Science and Technology of China（中国科学技术大学）；cmss.chinamobile.com（中移（苏州）软件技术有限公司）；Lin Gang Laboratory（林冈实验室）；ShanghaiTech University（上海科技大学）
Emergent Slow Thinking in LLMs as Inverse Tree Freezing
Hefei National Laboratory, University of Science and Technology of China（中国科学技术大学合肥微尺度物质科学国家实验室）；Hefei National Laboratory for Physical Sciences at the Microscale and Department of Modern Physics, University of Science and Technology of China（中国科学技术大学合肥微尺度物质科学国家实验室和现代物理系）；Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS（杭州高等研究院基础物理与数学科学学院）；DP Technology（DP技术）；Lanzhou Center for Theoretical Physics, Key Laboratory of Theoretical Physics of Gansu Province, Key Laboratory of Quantum Theory and Applications of MoE, Gansu Provincial Research Center for Basic Disciplines of Quantum Physics, Lanzhou University（兰州理论物理中心、甘肃省理论物理重点实验室、教育部量子理论与应用重点实验室、甘肃省量子物理基础学科省重点实验室、兰州大学）；AI for Science Institute, Beijing（北京人工智能科学研究院）
