top of page

​About​

​

I'm a Principal Researcher at Microsoft Research NYC. In this role, I broadly focus on building and evaluating generative AI, inspired by my research in cognitive neuroscience, reinforcement learning, and NeuroAI.  

Specifically, I study how humans and AI build models of the world and use them in memory, exploration, & planning. I build and test brain & behavior inspired algorithms for learning & reasoning, e.g., AI for gaming with Xbox. My approach combines reinforcement learning, neural networks, large language models, & machine learning with behavioral experiments, fMRI, & electrophysiology.

​

Most Fridays (4 PM ET) I cohost The Learning Salon (with John Krakauer & Melanie Mitchell).

I am delighted to serve as a mentor at the New Museum's New Inc, the incubator for creative science.

If you prefer podcasts, I discuss my work on AI and Rethinking intelligence with Ashley Lorens at the Microsoft Research AI frontiers podcast. Moreover, BrainInspired & Parsing Science have kindly featured earlier work, as well as our panels on Deep RL and Dopamine & Advancing Neuro Deep learning.

​

Academic Background​

My training is in cognitive computational neuroscience (via computer science and philosophy). I've previously worked at Columbia University, Electrophysiology, Memory, and Navigation Lab, did my postdoc at Princeton (where I collaborated with Ken Norman, Matt Botvinick, Jon Cohen, Nathaniel Daw), my PhD was in psychology (Berlin, Germany, Bernstein Center for Computational Neuroscience), BSc in software engineering (Tehran, Iran), & MSc in Philosophy of Science (Utrecht, Netherlands). 

​

Publications & preprints

​

​

​

​

​

​

​​

 

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

​

mem space time_edited.jpg

Ida Momennejad (2025) Memory and Planning in Brains and Machines: Multiscale Predictive Representations. Space, Time, and Memory, Edited by Lynn Nadel and Sara Aronovitz, forthcoming book in Oxford University Press.
[ OUP Book link,  arxiv ]

LLMcollective.png

Eleni Nisioti, Sebastian Risi, Ida Momennejad, Pierre-Yves Oudeyer, Clement Moulin-Frier (2024) Collective Innovation in Groups of Large Language Models. ALife 2024. [ arXiv ] 

Oliver Eberle, Thomas McGee, Hamza Gaffer, Taylor Webb, Ida Momennejad (2025) Position: We Need An Algorithmic Understanding of Generative AI. International Conference for Machine Learning, ICML 2025, [Spotlight, PDF ] 

fig5 (1)_edited.jpg

Ida Momennejad*, Hosein Hasanbeig*, Felipe Vieira Frujeri*, Hiteshi Sharma, Robert Ness, Nebojsa Jojic, Hamid Palangi, Jonathan Larson (2023)  Evaluating cognitive maps and planning in Large Language Models with CogEval.
[ arXiv ] [ GitHub ] [ conversation logs ] NeurIPS 2023.

Shuhao Fu, Andrew Jun Lee, Yixin Anna Wang, Ida Momennejad, Trevor Bihl, Hongjing Lu, Taylor Whittington Webb (2025) Evaluating Compositional Scene Understanding in Multimodal Generative Models. TMLR 2025. [arXiv]

unnamed-3.png
PFC_FIG.png

Taylor Webb*, Shanka Subra Mondal*, Yi Wan, Brian Krabach, Ida Momennejad (2023) A prefrontal cortex-inspired architecture for planning in Large Language Models.  

[ arXiv ] [ Github ]

cogeval_n7line_embedding_ICL0_Llama2_layer2.png

Safoora Yousefi, Leo Betthauser, Hosein Hasanbeig, Raphael Milliere, Ida Momennejad (2023) Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models. 

[ arXiv ]

st_1_gen_1.png

Hosein Hasanbeig, Hiteshi Sharma, Leo Betthauser, Felipe Vieira Frujeri,
Ida Momennejad (2023) ALLURE: Auditing and improving LLM-based evaluation of text using iterative in-context-learning. 

[ arXiv ]

Su_snapshot.png

Sugandha Sharma, Guy Davidson, Khimya Khetarpal, Anssi Kanervisto, Udit Arora, Katja Hofmann, Ida Momennejad (2024) Toward Human-AI Alignment in Large-Scale Multi-Player Games. 

[ arXiv ]

unnamed-10.png

Imitating Human Behavior with Diffusion Models (2023)  Pearce, Rashid, Kanervisto, Bigness, Sun, Georgescu, Mac, Zheng Tan, Momennejad, Hofmann, Devlin. ICLR 2023 [ link ]

unnamed-11.png

Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar (2023) Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning. CoLLAs 2023.

[ arXiv ]

unnamed.png

Stephanie Milani, Arthur Juliani, Ida Momennejad, Raluca Georgescu, Jaroslaw Rzpecki, Alison Shaw, Gavin Costello, Fei Fang, Sam Devlin, Katja Hofmann (2023)  Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games. ACM CHI (Conference on Human Factors in Computing Systems) 2023. [ arXiv ]

Phil Trabs B neuroAI plot.jpg
unnamed-9.png
sapines image_edited.jpg
AI-IGL.png
loca.png
unnamed-6.png
unnamed-7.png
Describeland-5.png
unnamed-3.png
philtransfig_edited.jpg
big fig_edited.jpg
neal_morton_fig.png

Ida Momennejad (2022)  A Rubric for Human-like Agents and NeuroAI.

Philosophical Transactions of the Royal Society B

[ journal link ]  [ free preprint arXiv ]

Eigen Memory Trees (2022) Mark Rucker, Jordan T. Ash, John Langford, Paul Mineiro, Ida Momennejad

In revision [ arXiv ]

Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS (2022)  Eleni Nisioti, Mateo Mahaut, Pierre-Yves Oudeyer, Ida Momennejad, Clément Moulin-Frier 

In revision [ arXiv ] [ Github Repo ]

Interaction-Grounded Learning with Action-inclusive Feedback
(2022) Tengyang Xie, Akanksha Saran, Dylan J. Foster, Lekan Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford

NeurIPS 2022 [ arXiv  preprint]

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods (2022)  Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen [ arXiv ]

ICML 2022

NeuroNav: A Library for Neuroscience Inspired Learning (2022) Julliani, Barnett, Davis, Sereno, Momennejad, RLDM 

[ arXiv ] [ Githib Repo ]

PARSR: Priority Adjusted Replay for Successor Representation (2022)

Barnett, Momennejad, RLDM 2022

​

Describeland: One-Shot Learning from a Demonstration with Hierarchical Latent Language (2022) Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Cote, Matthew Hausknecht,  Romain Laroche, Ida Momennejad, Harm Van Seijen, Benjamin Van Durme.  AAMAS.

How Humans Perceive Human-like Behavior in Video Game Navigation (2022) Zuniga*, Milani*, Leroy*, Rzepecki, Georgescu, Momennejad, Bignell, Sun, Shaw, Costello, Jacob, Devlin, Hofmann. 
CHI Late Breaking Work, 2022.    [ PDF ] 

https://github.com/microsoft/NTT

Momennejad I (2021) Collective Minds: Social Network Topology Shapes Collective Cognition. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences 377 (1843): 20200315.
[ PhilTrans , PDF ]

Brunec I,  Momennejad I (2021) Predictive Representations in Hippocampal and Prefrontal Hierarchies. Journal of Neuroscience 19 November 2021, JN-RM-1327-21.
[ JNeuro Link , free PDF ] 

Pudhiyidath A, Morton NW, Viveros Duran R, Schapiro AC,  Momennejad I, Hinojosa-Rowland DM, Molitor RJ, Preston AR (2022-accepted) Representations of temporal community structure in hippocampus and precuneus predict inductive reasoning decisions.

The Journal of Cognitive Neuroscience    [ bioRxiv ] 

learning salon.png

Momennejad I*, Krakauer J*, Sun C, Yezeretz E, Rajan K, Vogelstein J, Wyble B (2021) The Learning Salon: Toward a new participatory science. Neuron. 
[ Neuron link, PDF ]

MadaPhoto.jpeg

Vlasceanu M, Dudik M, Momennejad I (2021) Network Structure, Gender Diversity, and Interdisciplinarity Predict the Centrality of AI Organizations.
[ psyRxiv PDF ]

Evan_paper.png

Russek EM, Momennejad I, Botvinick M, Gershman S, Daw N (2021) Neural evidence for the successor representation in choice evaluation.
[ bioRxiv PDF ] 

unnamed-2.png
unnamed_edited.png
Rand_policy.png
big fig.png
graph_website_edited.jpg

Xie T, Lanford J, Mineiro P, Momennejad I (2021) Interaction Grounded Learning. ICML 2021. [ arXiv PDF ]

Devlin S*, Georgescu R*, Momennejad I*, Rzepecki J*, Zuniga E*, Costello G, Leroy G, Shaw A, Hofmann K (2021) Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation. ICML 2021. [ arXiv PDF ] 

https://github.com/microsoft/NTT​

Momennejad I (2020) Learning Structures: Predictive Representations, Replay, and Generalization. Current Opinions in Behavioral sciences.

[  PDF]

Brunec I, Momennejad I (2019) Predictive Representations in Hippocampal and Prefrontal Hierarchies.
[ bioRxiv preprint ]

Sievers B, Momennejad I (2019) SAMPL: Spreading Activation and Memory Plasticity Model.
[ bioRxiv preprint , Model Code on GitHub ]

instcosts_joyplot_meets1000_1000sim.png

Momennejad I, Sinclair S, Cikara M (2019) Computational justice: Simulating structural bias and interventions.
[ bioRxiv preprint , 04/21/2019: python workshop ]

sam_anxiety_tree.jpeg

Zorowitz S, Momennejad I, Daw N (2020) Anxiety, avoidance, and sequential evaluation. Computational Psychiatry, 0 0:0, February, 1–17.
[ Link to published paper , see 2019 bioRxiv preprint ]

Fig3_graph.png

Momennejad I, Duker A, Coman A (2019) Bridge ties bind collective memories. Nature Communications. 
[ Open access paper , Podcast ]

fig3model.png

Momennejad I, Norman KA, Cohen JD, Singh S, Lewis RL (2019). Rational use of Episodic and Working Memory: A Normative Account of Prospective Memory. BioRxiv, 580324 https://doi.org/10.1101/580324.
[ bioRxiv preprint, SfN poster ]

IM_multi-scale-successor_fig1.png

Momennejad I, Howard M (2018) Predicting the future with multi-scale successor representations.
[ bioRxiv preprint, status: in revision ]

reprev_fig_website.jpg

Momennejad I, Otto RA, Daw N, Norman KA (2018) Offline replay supports planning in human reinforcement learning. eLife 2018;7:e32548. 

[ eLife link, Talk at CCN 2017 , PDF,  open access dataset]

russek_fig_website.png

Russek E*, Momennejad I*,  Botvinick MM, Gershman SJ, Daw N (2017) Predictive representations can link model-based reinforcement learning to model-free mechanisms. Plos Comp Biol.
[ Journal link,  PDF, bioRxiv preprint,  CODE ]

SR_website.png

Momennejad I*, Russek E*, Cheong JH, Botvinick MM, Daw N, Gershman SJ (2017) The successor representation in human reinforcement learning: evidence from retrospective revaluation. Nature Human Behaviour, 1. [ Nat Hum Beh paper , PDF, free preprint , my python tutorials comparing SR & SR-Dyna,  blogpost from Deepmind ] 

collectivemem_websote.png

Coman A, Momennejad I, Drach R, Geana A (2016) Mnemonic convergence in social networks: The emergent properties of cognition at a collective level. PNAS. doi: 10.1073/pnas.1525569113.
[ Journal link , Podcast ]

task_rewardmap.png

Wisniewsky D, Reverberi C, Momennejad I, Kahnt T, Haynes J-D (2016) The role of parietal cortex in the representation of task-reward-association. The Journal of Neuroscience. [ Journal link ] 

compositional.png
jenruo_results.png

Haynes J-D, Wisniewsky D, Gorgen K, Momennejad I, Reverberi C (2015) fMRI decoding of intentions: compositionality, hierarchy, and prospective memory. Brain-Computer Interface (BCI), 3rd International Winter Conference. doi: 10.1109/IWW-BCI.2015.7073031. [ IEEE link ]

Momennejad I, Haynes J-D (2013) Encoding of prospective tasks in the human prefrontal cortex under varying task load. The Journal of Neuroscience 33(44):17342-17349. [ Journal link + PDF file ]

what_when.png

Momennejad I, Haynes J-D (2012) Human anterior prefrontal cortex encodes the 'what' and 'when' of future intentions. Neuroimage 61(1):139-48.

[ Journal link + PDF file ]

​

​​

 

​

Recent Teaching

​

​​

​

​

Sample Talks and Workshops (April-September 2019)

​

​

April 21, 1-5 PM: Computational Justice Workshop (hands-on agent-based simulation in Python), Heart of the Machine series, Pioneerworks, Brooklyn, NY

​

May 13-14: Context and Episodic Memory (CEMS), Philadelphia, PA

 

May 16-18: Control Processes 2019, Brown University, Providence, RI

​

May 28-29: Talk and visit, Computational Neuroscience Center, University of Washington, Seatle, WA

​

July 10, 1-5PM: Structure for Efficient Reinforcement Learning (SERL) Workshop
4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Montreal, Canada

​

August 8-17: "Cognitive Maps" at MIND19 summer school for computational methods in neuroscience at Dartmouth​

​

September 10-13: What is biological Computation? Santa Fe Institute

​

​

​

Book chapters 

​

  • Momennejad I, Allahyari M (2017) Refiguring: in Conversation. Futureproof, Haverford College, Haverford, PA, pp 16-31.

  • Momennejad I (2011) Thinking in movements, rehearsing freedom. In: Wagner L and Gomes-Carrillo de Castro Eds., Sounds, Space, Body, a process. Ernst Schering Foundation and Association of Neuroesthetics: Berlin, pp:115-125.

  • Momennejad I (2011) Seeing with eyes closed: the neuro-epistemology of perceptual reality. In: Agudio E and Franke I Eds., Seeing with eyes closed. Association of Neuroesthetics: Berlin, pp:15-21.

  • Momennejad I and Franke I (2011) Two practices of seeing with eyes closed: contemporary art and science in dialogue. In: Agudio E and Franke I Eds., Seeing with eyes closed. Association of Neuroesthetics: Berlin, pp:9-13.

​

 

 

Media: Talks, outreach, press

 

idamo [at] microsoft.com
​
bottom of page