NeuroAgents Lab

Welcome to the NeuroAgents lab. Our group studies the science and societal implications of intelligent systems. Learn more here, and check out the Research page for examples of our work!

This page lists current lab members and (eventual!) alumni. If you’re interested in joining, please see the Contact page for guidance.

Lab Announcements

• [June 2026] 📣 Aran will give an invited talk, “Intrinsic Barriers and Practical Pathways to Alignment”, in Paris in honor of Nobel Prize winner Robert Aumann's 96th birthday.
• [June 2026] 🚀 New preprint from Jeremy, Abishek, Yu-Rou, Yuchen, Zico, and Aran on ROGUE: misaligned agent behavior arising from ordinary computer use.
• [Mar 2026] 🚀 New paper from Aran, What Capable Agents Must Know, to appear at UAI 2026.
• [Mar 2026] 🚀 Reece presented Intrinsic Goals for Autonomous Agents at COSYNE 2026.
• [Feb 2026] 📣 Aran gave a NeuroML Workshop keynote at the University of Chicago on behavior-shaped recurrent circuits.
• [Feb 2026] 📣 Aran gave a Stanford guest lecture on using embodied agents to reverse-engineer natural intelligence.
• [Jan 2026] 🚀 Aran presented Core Safety Values for Provably Corrigible Agents at the AAAI Machine Ethics Workshop.
• [Jan 2026] 🚀 Aran’s paper Intrinsic Barriers and Practical Pathways for Human-AI Alignment was selected for oral presentation at AAAI.
• [Dec 2025] 📣 Aran gave invited talks at the BAMΞ Mathematical Phenomenology Sprint and the University of Toronto Robotics Institute.
• [Dec 2025] 🚀 Congrats to Trinity and Yuchen on their NeurIPS oral paper, Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain.
• [Dec 2025] 🚀 Congrats to Reece, Alyn, Felix, Xaq, Leo, and Aran on their NeurIPS paper, Intrinsic Goals for Autonomous Agents.
• [Nov 2025] 📣 Aran gave invited AI alignment lectures at CMU on intrinsic barriers and practical pathways to alignment.
• [Oct 2025] 🏆 Congratulations Reece Keller for getting the Best Student Talk Award at the Champalimaud Research Symposium (CRSy25) for “Autonomous Behavior and Whole-Brain Dynamics Emerge in Embodied Zebrafish Agents with Model-Based Intrinsic Motivation.”
• [Oct 2025] 📣 Aran gave an invited talk at the inaugural UK AISI Alignment Conference on intrinsic barriers and practical pathways to alignment.
• [Oct 2025] 🚀 Trinity and Yuchen presented Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain at CRSy25.
• [Sept 2025] 📣 Aran gave the CMU Robotics Institute Seminar on reverse-engineering natural intelligence with embodied agents.
• [Sept 2025] 🎙️ Aran appeared on the Information Bottleneck Podcast.
• [Aug 2025] 📣 Aran gave an ILIAD 2025 talk on alignment and formal corrigibility guarantees.
• [Aug 2025] 🚀 New CCN paper on model-brain comparison using inter-animal transforms.
• [July 2025] 🚀 New preprint from Aran on core safety values for provably corrigible agents.
• [June 2025] 🏆 Congratulations Trinity Chung for getting the NSF Graduate Research Fellowship for “Towards 99.9% Robot Performance: Brain-inspired Visuo-Tactile Models for Robust Robot Learning in Real World Environments.”
• [June 2025] 📣 Aran gave an invited talk at the FENS Regional Meeting on explaining heterogeneity in medial entorhinal cortex with task-driven neural networks.
• [May 2025] 🚀 New preprint from Aran on an AI capability threshold for rent-funded universal basic income.
• [May 2025] 🎙️ Aran joined CMU Faculty Dialogues: Building Bridges Between AI and the Brain.
• [May 2025] 📣 Aran gave an invited Foresight Institute talk on barriers and pathways to human-AI alignment.
• [Apr 2025] 🏆 Congratulations Jeremy Tien for getting the NSF Graduate Research Fellowship for “Provably Safe and Beneficial Artificial Intelligence Agents.”
• [Apr 2025] 📣 Aran gave a MyoSuite MyoTalks seminar on using Embodied AI for “why” questions in systems neuroscience.
• [Mar 2025] 📣 Aran gave invited talks at the Cosyne workshop on agent-based models in neuroscience and the NeuroAI Emerging Leaders Webinar Series.
• [Mar 2025] 🎙️ Aran appeared on the Brain Inspired Podcast for “The NeuroAI Turing Test.”
• [Mar 2025] 📣 Aran gave a Ploutos Fireside Chat on barriers and pathways to human-AI alignment.
• [Feb 2025] 🚀 New position paper from Jenelle, Meenakshi, Apurva, and Aran on why brain-model evaluations need the NeuroAI Turing Test.
• [Feb 2025] 🎙️ Aran appeared on the Ones Changing The World Podcast for “The Future of AI: Can We Copy Animal Brains for General Intelligence?”
• [Feb 2025] 📣 Aran gave an EPFL Special BMI Seminar on using embodied agents for “why” questions in systems neuroscience.
• [2025] 🏆 Aran received the Whole Brain Architecture Initiative Incentive Award.
• [Dec 2024] 📣 Aran gave an invited talk at the CMU Neuroscience Institute Retreat on using Embodied AI for “why” questions in systems neuroscience.
• [Nov 2024] 📣 Aran gave an invited talk at Google Research’s Theory & Practice of Foundation Models Workshop on model improvements from reverse-engineering natural intelligence.
• [Oct 2024] 📣 Aran presented “Neural Foundations of Mental Simulation” at SfN 2024.
• [Sept 2024] 🎙️ Aran joined the RagaAI Webinar, “The Future of GenAI - Agentic Frameworks and More.”
• [2024] 🏆 Aran received the Burroughs Wellcome Fund Career Award at the Scientific Interface (BWF CASI).

Principal Investigator

• Aran Nayebi – Assistant Professor, Carnegie Mellon University.

PhD Students

• Reece Keller - Program in Neural Computation. Co-advised with Xaq Pitkow.
• Yuchen Shen - Machine Learning Department.
• Jeremy Tien - Machine Learning Department. Co-advised with Zico Kolter.

Masters Students

• Trinity Chung - Robotics Institute.
• Richard (Yusen) Hu - Robotics Institute.
• Jayant Sharma - AI + Biomedical Engineering.
• Alyn Kirsch Tornell - Robotics Institute.

Visiting Students

• Declan Kutscher - Computer Science, Masters Student, University of Pittsburgh.
• Xueqiao Sun - Computer Science and Finance, Undergraduate Student, Tsinghua University.