Training Large Reasoning Models: Neuro-Symbolic Wednesdays

​📘 This week, Dr. Asim Munawar from IBM’s Watson Research will examine how integrating Neuro-Symbolic AI approaches with large language models (LLMs) can enhance their reasoning, interpretability, and reliability.

Dr. Asim Munawar is a Project Lead at IBM’s Watson Research Center in New York, where he heads efforts to enhance reasoning, planning, and agentic workflows in enterprise-scale large language models. With over 15 years of experience in AI – more than a decade of it at IBM Research – he has held key leadership roles, including Manager and Program Director for Neuro-Symbolic AI https://asimmunawar.github.io

​This presentation will explore architectures that combine symbolic logic, structured representations, and deep learning, and outlines strategies to address limitations such as brittleness, hallucination, and lack of transparency in current LLMs.

​📝 Bonus: The DeepSeek paper will be covered in Asim's presentation.
https://arxiv.org/abs/2501.12948

​

​
🔬 Join us for an interactive session exploring Neuro-Symbolic AI
💬 https://discord.gg/h8NVzwnysW

​Whether you’re a researcher, engineer, or simply curious about the cutting edge of AI, you’ll find an engaging space to learn, connect, and exchange ideas.

Event Format:
🔍 Reading Group
🎙️ Panel Discussion
🧩 Tutorials/Workshop Series
💬 Research Roundtable
🛠️ Open-Source Project Review
📄 Paper Pitch
🤝 Collaboration Hour
🍵 Networking Mixer