Disentangling visual attributes with neuro-vector-symbolic architectures, in-memory computing, and device noise Technical note Abu Sebastian, Abbas Rahimi, and Geethan Karunaratne 30 Mar 2023 AI AI Hardware Neuro-symbolic AI Disentangling visual attributes with neuro-vector-symbolic architectures, in-memory computing, and device noise Neuro-symbolic AI This AI could likely beat you at an IQ test Research Abbas Rahimi and Michael Hersche 09 Mar 2023 AI Neuro-symbolic AI This AI could likely beat you at an IQ test Neuro-symbolic AI How IBM Research is accelerating discoveries in the fight against COVID-19 Research Mike Murphy 12 Oct 2021 10 minute read Exploratory Science Healthcare Impact Science Neuro-symbolic AI How IBM Research is accelerating discoveries in the fight against COVID-19 Exploratory Science Neuro-symbolic AI AI, you have a lot of explaining to do Release Dinesh Garg, Parag Singla, Dinesh Khandelwal, Shourya Aggarwal, Divyanshu Mandowara, and Vishwajeet Agrawal 02 Aug 2021 5 minute read Explainable AI Generative AI Knowledge and Reasoning Natural Language Processing Neuro-symbolic AI Trustworthy AI AI, you have a lot of explaining to do Knowledge and Reasoning Natural Language Processing Neuro-symbolic AI IBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021 Release Dan Gutfreund, Abhishek Bhandwaldar, and Chuang Gan 19 Jul 2021 6 minute read AI Knowledge and Reasoning Neuro-symbolic AI IBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021 Knowledge and Reasoning Neuro-symbolic AI Mimicking the brain: Deep learning meets vector-symbolic AI Research Abu Sebastian and Abbas Rahimi 29 Apr 2021 4 minute read AI Neuro-symbolic AI Mimicking the brain: Deep learning meets vector-symbolic AI Neuro-symbolic AI See more of our work on Neuro-symbolic AI Neuro-symbolic AI aims to give machines true common sense Accelerator Technologies We're developing technological solutions to assist subject matter experts with their scientific workflows by enabling the Human-AI co-creation process. Accelerator Technologies We're developing technological solutions to assist subject matter experts with their scientific workflows by enabling the Human-AI co-creation process. Transformer Circuits Can Realize Clustering Algorithms Kenneth Clarkson Lior Horesh et al. 2026 ICML 2026 Conference paper Transformer Circuits Can Realize Clustering Algorithms Kenneth Clarkson Lior Horesh et al.

Kenneth Clarkson Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning Massimiliano Pronesti Anya Belz et al. 2026 ACL 2026 Paper Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning Massimiliano Pronesti Anya Belz et al. Massimiliano Pronesti Unsupervised Cycle Detection in Agentic Applications Felix George Divya Pathak et al. 2026 ICPE 2026 Short paper Unsupervised Cycle Detection in Agentic Applications Felix George Divya Pathak et al. Unifying Concept Representation Learning Amit Dhurandhar Amir-hossein Karimi et al. 2026 ICLR 2026 Workshop Unifying Concept Representation Learning Amit Dhurandhar Amir-hossein Karimi et al. Amit Dhurandhar Amir-hossein Karimi Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs Hussein Abdallah Ibrahim Abdelaziz et al. 2026 EACL 2026 Conference paper Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs Hussein Abdallah Ibrahim Abdelaziz et al. Hussein Abdallah Ibrahim Abdelaziz SOFAI-LM: A Cognitive Architecture for Building Efficient and Reliable Reasoning Systems with LLMs Vedant Khandelwal Francesca Rossi et al. 2026 AAAI 2026 Tutorial SOFAI-LM: A Cognitive Architecture for Building Efficient and Reliable Reasoning Systems with LLMs Vedant Khandelwal Francesca Rossi et al. Vedant Khandelwal Francesca Rossi Neuro-symbolic AI research at the MIT-IBM Watson AI Lab Read more about our work in neuro-symbolic AI from the MIT-IBM Watson AI Lab. Our researchers are working to usher in a new era of AI where machines can learn more like the way humans do, by connecting words with images and mastering abstract concepts. Computer Vision Computer Science Knowledge and Reasoning Natural Language Processing