#  Publications 

 



  Download 156 citations  download- [BibTeX](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=bibtex)
- [EndNote X3 XML](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=endnote8)
- [EndNote 7 XML](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=endnote7)
- [Endnote tagged](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=tagged)
- [Marc](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=marc)
- [PubMedId](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=pubmed_id)
- [RIS](/bibcite/export?pager_style=show_more&number_of_items=50&sort_field=bibcite_year--desc&taxonomy_filters=&&&format=ris)
 


 

### 2026

B. S. Ruben and C. Pehlevan,

“[Heterogeneous Instructive Signals Enable Ensemble Learning in Cerebellar Cortex](https://www.biorxiv.org/content/10.64898/2026.05.06.723116v1)”, *biorXiv*, 2026.





 

 

B. S. Ruben and C. Pehlevan,

“[Heterogeneous Instructive Signals Enable Ensemble Learning in Cerebellar Cortex](https://www.biorxiv.org/content/10.64898/2026.05.06.723116v1)”, *biorXiv*, 2026.





 

 

 

 

C. Lauditi, C. Pehlevan*, and B. Bordelon*,

“[Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer](https://arxiv.org/abs/2605.07870)”, *arXiv preprint arXiv:2605.07870*, 2026.





 

 

C. Lauditi, C. Pehlevan*, and B. Bordelon*,

“[Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer](https://arxiv.org/abs/2605.07870)”, *arXiv preprint arXiv:2605.07870*, 2026.





 

 

 

 

M. Uzun, M. Erdogan, C. Pehlevan, and A. T. Erdogan,

“[Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment](https://arxiv.org/abs/2605.30638)”, *arXiv preprint arXiv:2605.30638* , 2026.





 

 

M. Uzun, M. Erdogan, C. Pehlevan, and A. T. Erdogan,

“[Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment](https://arxiv.org/abs/2605.30638)”, *arXiv preprint arXiv:2605.30638* , 2026.





 

 

 

 

K. Takanami and C. Pehlevan,

“[An Asymptotic Theory of Chain-of-Thought in In-Context Learning](https://arxiv.org/abs/2606.03217)”, *arXiv preprint arXiv:2606.03217*, 2026.





 

 

K. Takanami and C. Pehlevan,

“[An Asymptotic Theory of Chain-of-Thought in In-Context Learning](https://arxiv.org/abs/2606.03217)”, *arXiv preprint arXiv:2606.03217*, 2026.





 

 

 

 

A. Atanasov, B. Bordelon, J. A. Zavatone-Veth, C. Paquette, and C. Pehlevan,

“[Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models](https://link.intlpress.com/JDetail/2043359039483547650)”, *Advances in Theoretical and Mathematical Physics*, vol. 30, no. 1, p. 36, 2026.





 

 

A. Atanasov, B. Bordelon, J. A. Zavatone-Veth, C. Paquette, and C. Pehlevan,

“[Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models](https://link.intlpress.com/JDetail/2043359039483547650)”, *Advances in Theoretical and Mathematical Physics*, vol. 30, no. 1, p. 36, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-05/Atanasov_etal_ATMP_2026.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-05/Atanasov_etal_ATMP_2026.pdf)
 
 

C. Lauditi, B. Bordelon, and C. Pehlevan,

“[Transfer Learning in Infinite Width Feature Learning Networks](https://openreview.net/forum?id=Oox4QOhmi9)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

C. Lauditi, B. Bordelon, and C. Pehlevan,

“[Transfer Learning in Infinite Width Feature Learning Networks](https://openreview.net/forum?id=Oox4QOhmi9)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Lauditi_etal_ICLR_2026_0.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Lauditi_etal_ICLR_2026_0.pdf)
 
 

J. A. Zavatone-Veth and C. Pehlevan,

“[A note on the dynamics of extended-context disordered kinetic spin models](https://iopscience.iop.org/article/10.1088/1751-8121/ae38a4)”, *Journal of Physics A: Mathematical and Theoretical*, vol. 59, no. 4, 2026.





 

 

J. A. Zavatone-Veth and C. Pehlevan,

“[A note on the dynamics of extended-context disordered kinetic spin models](https://iopscience.iop.org/article/10.1088/1751-8121/ae38a4)”, *Journal of Physics A: Mathematical and Theoretical*, vol. 59, no. 4, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-01/Zavatone-Veth_Pehlevan_JPhysA_2026_0.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-01/Zavatone-Veth_Pehlevan_JPhysA_2026_0.pdf)
 
 

A. Atanasov, J. A. Zavatone-Veth, and C. Pehlevan,

“[Scaling and renormalization in high-dimensional regression ](https://iopscience.iop.org/article/10.1088/1742-5468/ae4bba)”, *J. Stat. Mech.*, vol. 2026, 2026.





 

 

A. Atanasov, J. A. Zavatone-Veth, and C. Pehlevan,

“[Scaling and renormalization in high-dimensional regression ](https://iopscience.iop.org/article/10.1088/1742-5468/ae4bba)”, *J. Stat. Mech.*, vol. 2026, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-05/Atanasov_etal_JSTAT_2026.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-05/Atanasov_etal_JSTAT_2026.pdf)
 
 

W. Qian and C. Pehlevan,

“[Discovering alternative solutions beyond the simplicity bias in recurrent neural networks](https://openreview.net/forum?id=8fViWZ0yZJ)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

W. Qian and C. Pehlevan,

“[Discovering alternative solutions beyond the simplicity bias in recurrent neural networks](https://openreview.net/forum?id=8fViWZ0yZJ)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

 

 

M. Letey, J. A. Zavatone-Veth, Y. M. Lu, and C. Pehlevan,

“[Pretrain-Test Task Alignment Governs Generalization in In-Context Learning](https://openreview.net/forum?id=KZLeg0MQ2r)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

M. Letey, J. A. Zavatone-Veth, Y. M. Lu, and C. Pehlevan,

“[Pretrain-Test Task Alignment Governs Generalization in In-Context Learning](https://openreview.net/forum?id=KZLeg0MQ2r)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Letey_etal_ICLR_2026.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Letey_etal_ICLR_2026.pdf)
 
 

B. Bordelon, M. I. Letey, and C. Pehlevan,

“[Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time](https://openreview.net/forum?id=qA42mWsnbl)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

B. Bordelon, M. I. Letey, and C. Pehlevan,

“[Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time](https://openreview.net/forum?id=qA42mWsnbl)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Bordelon_etal_ICLR_2026_0.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Bordelon_etal_ICLR_2026_0.pdf)
 
 

A. Meterez, D. Morwani, J. Wu, C.-A. Oncescu, C. Pehlevan, and S. Kakade,

“[Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling](https://openreview.net/forum?id=Nj0XBF2o7z)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

A. Meterez, D. Morwani, J. Wu, C.-A. Oncescu, C. Pehlevan, and S. Kakade,

“[Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling](https://openreview.net/forum?id=Nj0XBF2o7z)”, *International Conference on Learning Representations (ICLR)*, 2026.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Meterez_etal_ICLR_2026.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Meterez_etal_ICLR_2026.pdf)
 
 

M. Yaghoubi *et al.*,

“[Predictive Coding of Reward in the Hippocampus](https://www.nature.com/articles/s41586-025-09958-0)”, *Nature*, 2026.





 

 

M. Yaghoubi *et al.*,

“[Predictive Coding of Reward in the Hippocampus](https://www.nature.com/articles/s41586-025-09958-0)”, *Nature*, 2026.





 

 

 

 

I. Halder and C. Pehlevan,

“[Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling](https://arxiv.org/abs/2512.19905)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

I. Halder and C. Pehlevan,

“[Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling](https://arxiv.org/abs/2512.19905)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

 

 

B. Bordelon and C. Pehlevan,

“[Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning](https://arxiv.org/abs/2601.01010)”, *arXiv preprint arXiv:2601.01010* , 2026.





 

 

B. Bordelon and C. Pehlevan,

“[Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning](https://arxiv.org/abs/2601.01010)”, *arXiv preprint arXiv:2601.01010* , 2026.





 

 

 

 

T. Jiang, B. Bordelon, C. Pehlevan, and B. Hanin,

“[Hyperparameter Transfer with Mixture-of-Expert Layers](https://arxiv.org/abs/2601.20205)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

T. Jiang, B. Bordelon, C. Pehlevan, and B. Hanin,

“[Hyperparameter Transfer with Mixture-of-Expert Layers](https://arxiv.org/abs/2601.20205)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

 

 

A. Meterez*, P. A. Nair*, D. Morwani*, C. Pehlevan, and S. Kakade,

“[Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging](https://arxiv.org/abs/2602.03702)”, *arXiv preprint arXiv:2602.03702*, 2026.





 

 

A. Meterez*, P. A. Nair*, D. Morwani*, C. Pehlevan, and S. Kakade,

“[Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging](https://arxiv.org/abs/2602.03702)”, *arXiv preprint arXiv:2602.03702*, 2026.





 

 

 

 

Y. Liu, Z. Liu, C. Pehlevan, and J. Gore,

“[Universal One-third Time Scaling in Learning Peaked Distributions](https://arxiv.org/abs/2602.03685)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

Y. Liu, Z. Liu, C. Pehlevan, and J. Gore,

“[Universal One-third Time Scaling in Learning Peaked Distributions](https://arxiv.org/abs/2602.03685)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

 

 

B. Wang, J. Zavatone-Veth, and C. Pehlevan,

“[A Random Matrix Theory Perspective on the Consistency of Diffusion Models](https://arxiv.org/abs/2602.02908)”, *International Conference on Machine Learning (ICML) (Oral)*, 2026.





 

 

B. Wang, J. Zavatone-Veth, and C. Pehlevan,

“[A Random Matrix Theory Perspective on the Consistency of Diffusion Models](https://arxiv.org/abs/2602.02908)”, *International Conference on Machine Learning (ICML) (Oral)*, 2026.





 

 

 

 

W. L. Tong, E. Cakar, and C. Pehlevan,

“[Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces ](https://arxiv.org/abs/2602.14404)”, *arXiv preprint arXiv:2602.14404*, 2026.





 

 

W. L. Tong, E. Cakar, and C. Pehlevan,

“[Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces ](https://arxiv.org/abs/2602.14404)”, *arXiv preprint arXiv:2602.14404*, 2026.





 

 

 

 

D. G. Clark*, B. Bordelon*, J. A. Zavatone-Veth*, and C. Pehlevan,

“[Structure, disorder, and dynamics in task-trained recurrent neural circuits](https://www.biorxiv.org/content/10.64898/2026.03.02.708943v1)”, *biorXiv*, 2026.





 

 

D. G. Clark*, B. Bordelon*, J. A. Zavatone-Veth*, and C. Pehlevan,

“[Structure, disorder, and dynamics in task-trained recurrent neural circuits](https://www.biorxiv.org/content/10.64898/2026.03.02.708943v1)”, *biorXiv*, 2026.





 

 

 

 

I. Halder, A. Banerjee, and C. Pehlevan,

“[Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover](https://arxiv.org/abs/2603.11331)”, *arXiv preprint arXiv:2603.11331*, 2026.





 

 

I. Halder, A. Banerjee, and C. Pehlevan,

“[Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover](https://arxiv.org/abs/2603.11331)”, *arXiv preprint arXiv:2603.11331*, 2026.





 

 

 

 

A. Lee*, G. Kumar*, B. Bordelon, and C. Pehlevan,

“[CompleteP for RL: Maintaining Feature Learning When Scaling Deep Reinforcement Learning](https://openreview.net/forum?id=3uXAGWqCny)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

A. Lee*, G. Kumar*, B. Bordelon, and C. Pehlevan,

“[CompleteP for RL: Maintaining Feature Learning When Scaling Deep Reinforcement Learning](https://openreview.net/forum?id=3uXAGWqCny)”, *International Conference on Machine Learning (ICML)*, 2026.





 

 

 

 

 



### 2025

J. A. Zavatone-Veth, S. Yang*, J. A. Rubinfien*, and C. Pehlevan,

“[How does training shape the Riemannian geometry of neural network representations?](https://openreview.net/forum?id=BaVIDhh7bj)”, *NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations (NeurReps) Proceedings (Oral)*, 2025.





 

 

J. A. Zavatone-Veth, S. Yang*, J. A. Rubinfien*, and C. Pehlevan,

“[How does training shape the Riemannian geometry of neural network representations?](https://openreview.net/forum?id=BaVIDhh7bj)”, *NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations (NeurReps) Proceedings (Oral)*, 2025.





 

 

 

 

S. Yang, P. Liu, and C. Pehlevan,

“[Convex Relaxation for Solving Large-Margin Classifiers in Hyperbolic Space ](https://openreview.net/forum?id=eIPwJgadfZ)”, *Transactions on Machine Learning Research*, 2025.





 

 

S. Yang, P. Liu, and C. Pehlevan,

“[Convex Relaxation for Solving Large-Margin Classifiers in Hyperbolic Space ](https://openreview.net/forum?id=eIPwJgadfZ)”, *Transactions on Machine Learning Research*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-04/Yang_etal_TMLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-04/Yang_etal_TMLR_2025.pdf)
 
 

S. Yang, J. A. Zavatone-Veth, and C. Pehlevan,

“[Spectral regularization for adversarially-robust representation learning](https://ieeexplore.ieee.org/abstract/document/11443939)”, *2025 Asilomar Conference on Signals, Systems, and Computers*, 2025.





 

 

S. Yang, J. A. Zavatone-Veth, and C. Pehlevan,

“[Spectral regularization for adversarially-robust representation learning](https://ieeexplore.ieee.org/abstract/document/11443939)”, *2025 Asilomar Conference on Signals, Systems, and Computers*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Yang_etal_Asilomar_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Yang_etal_Asilomar_2025.pdf)
 
 

A. Atanasov*, A. Meterez*, J. B. Simon*, and C. Pehlevan,

“[The Optimization Landscape of SGD Across the Feature Learning Strength](https://openreview.net/forum?id=iEfdvDTcZg)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

A. Atanasov*, A. Meterez*, J. B. Simon*, and C. Pehlevan,

“[The Optimization Landscape of SGD Across the Feature Learning Strength](https://openreview.net/forum?id=iEfdvDTcZg)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Atanasov_etal_ICLR_2025_0.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Atanasov_etal_ICLR_2025_0.pdf)
 
 

E. Attias, C. Pehlevan, and D. Obeid,

“[Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustness ](https://ieeexplore.ieee.org/document/11443940)”, *2025 Asilomar Conference on Signals, Systems, and Computers*, 2025.





 

 

E. Attias, C. Pehlevan, and D. Obeid,

“[Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustness ](https://ieeexplore.ieee.org/document/11443940)”, *2025 Asilomar Conference on Signals, Systems, and Computers*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Attias_etal_Asilomar_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-04/Attias_etal_Asilomar_2025.pdf)
 
 

W. Tong and C. Pehlevan,

“[MLPs Learn In-Context on Regression and Classification Tasks](https://openreview.net/forum?id=MbX0t1rUlp)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

W. Tong and C. Pehlevan,

“[MLPs Learn In-Context on Regression and Classification Tasks](https://openreview.net/forum?id=MbX0t1rUlp)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Tong%26Pehlevan_ICLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Tong%26Pehlevan_ICLR_2025.pdf)
 
 

H. Cui, C. Pehlevan, and Y. M. Lu,

“[A solvable model of learning generative diffusion: theory and insights](https://openreview.net/forum?id=5b5wZg6Zeo)”, *Advances in Neural Information Processing Systems (NeurIPS), 2025*, 2025.





 

 

H. Cui, C. Pehlevan, and Y. M. Lu,

“[A solvable model of learning generative diffusion: theory and insights](https://openreview.net/forum?id=5b5wZg6Zeo)”, *Advances in Neural Information Processing Systems (NeurIPS), 2025*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-11/Cui_etal_NeurIPS_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-11/Cui_etal_NeurIPS_2025.pdf)
 
 

B. Bordelon and C. Pehlevan,

“[Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer](https://openreview.net/forum?id=SEj9uopOWP)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

B. Bordelon and C. Pehlevan,

“[Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer](https://openreview.net/forum?id=SEj9uopOWP)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Bordelon%26Pehlevan_ICML_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Bordelon%26Pehlevan_ICML_2025.pdf)
 
 

C. Lauditi, B. Bordelon, and C. Pehlevan,

“[Adaptive kernel predictors from feature-learning infinite limits of neural networks](https://openreview.net/forum?id=NLiwENWuaJ)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

C. Lauditi, B. Bordelon, and C. Pehlevan,

“[Adaptive kernel predictors from feature-learning infinite limits of neural networks](https://openreview.net/forum?id=NLiwENWuaJ)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Lauditi_etal_ICML_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Lauditi_etal_ICML_2025.pdf)
 
 

H. T. Chaudhry, M. Kulkarni, and C. Pehlevan,

“[Test-time scaling meets associative memory: Challenges in subquadratic models](https://openreview.net/forum?id=QjRZNhfOVL)”, *ICLR Workshop: New Frontiers in Associative Memories*, 2025.





 

 

H. T. Chaudhry, M. Kulkarni, and C. Pehlevan,

“[Test-time scaling meets associative memory: Challenges in subquadratic models](https://openreview.net/forum?id=QjRZNhfOVL)”, *ICLR Workshop: New Frontiers in Associative Memories*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Chaudhry_etal_NFAM_ICLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Chaudhry_etal_NFAM_ICLR_2025.pdf)
 
 

G. Kumar, B. Bordelon, J. A. Zavatone-Veth, and C. Pehlevan,

“[Place Field Representation Learning During Policy Learning](https://openreview.net/forum?id=P74KSHieDP)”, *Second Workshop on Representational Alignment at ICLR 2025*, 2025.





 

 

G. Kumar, B. Bordelon, J. A. Zavatone-Veth, and C. Pehlevan,

“[Place Field Representation Learning During Policy Learning](https://openreview.net/forum?id=P74KSHieDP)”, *Second Workshop on Representational Alignment at ICLR 2025*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Kumar_et_al_Re-Align_ICLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Kumar_et_al_Re-Align_ICLR_2025.pdf)
 
 

T. Kumar, B. Bordelon, C. Pehlevan, V. N. Murthy, and S. J. Gershman,

“[Do Mice Grok? Glimpses of Hidden Progress During Overtraining in Sensory Cortex ](https://openreview.net/forum?id=oYemKnlIrO)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

T. Kumar, B. Bordelon, C. Pehlevan, V. N. Murthy, and S. J. Gershman,

“[Do Mice Grok? Glimpses of Hidden Progress During Overtraining in Sensory Cortex ](https://openreview.net/forum?id=oYemKnlIrO)”, *International Conference on Learning Representations (ICLR)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Kumar_Bordelon_etal_ICLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-03/Kumar_Bordelon_etal_ICLR_2025.pdf)
 
 

W. L. Tong and C. Pehlevan,

“[Learning richness modulates equality reasoning in neural networks](https://openreview.net/forum?id=QaDfpS2dg2)”, *Computational Cognitive Neuroscience (CCN) Proceedings*, 2025.





 

 

W. L. Tong and C. Pehlevan,

“[Learning richness modulates equality reasoning in neural networks](https://openreview.net/forum?id=QaDfpS2dg2)”, *Computational Cognitive Neuroscience (CCN) Proceedings*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-07/Tong%26Pehlevan_CCN_Proceedings_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-07/Tong%26Pehlevan_CCN_Proceedings_2025.pdf)
 
 

G. Kumar, A. Manoogian, W. Qian, C. Pehlevan*, and S. A. Rhoads*,

“[Neurocomputational underpinnings of suboptimal beliefs in recurrent neural network-based agents](https://openreview.net/forum?id=4eOcvVeZSl&noteId=VuB95Qr7Oh)”, *Computational Cognitive Neuroscience (CCN) Proceedings*, 2025.





 

 

G. Kumar, A. Manoogian, W. Qian, C. Pehlevan*, and S. A. Rhoads*,

“[Neurocomputational underpinnings of suboptimal beliefs in recurrent neural network-based agents](https://openreview.net/forum?id=4eOcvVeZSl&noteId=VuB95Qr7Oh)”, *Computational Cognitive Neuroscience (CCN) Proceedings*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-07/Kumar_et_al_CCN_Proceedings_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-07/Kumar_et_al_CCN_Proceedings_2025.pdf)
 
 

B. Bordelon, J. Cotler, C. Pehlevan, and J. A. Zavatone-Veth,

“[Dynamically Learning to Integrate in Recurrent Neural Networks](https://arxiv.org/abs/2503.18754)”, *arXiv preprint arXiv:2503.18754*, 2025.





 

 

B. Bordelon, J. Cotler, C. Pehlevan, and J. A. Zavatone-Veth,

“[Dynamically Learning to Integrate in Recurrent Neural Networks](https://arxiv.org/abs/2503.18754)”, *arXiv preprint arXiv:2503.18754*, 2025.





 

 

 

 

R. Zhao*, A. Meterez*, S. Kakade, C. Pehlevan, S. Jelassi, and E. Malach,

“[Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining](https://openreview.net/forum?id=dp4KWuSDzj#discussion)”, *The Conference on Language Modeling (COLM)*, 2025.





 

 

R. Zhao*, A. Meterez*, S. Kakade, C. Pehlevan, S. Jelassi, and E. Malach,

“[Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining](https://openreview.net/forum?id=dp4KWuSDzj#discussion)”, *The Conference on Language Modeling (COLM)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Zhao_etal_COLM_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Zhao_etal_COLM_2025.pdf)
 
 

Y. M. Lu, M. I. Letey, J. A. Zavatone-Veth*, A. Maiti*, and C. Pehlevan,

“[Asymptotic theory of in-context learning by linear attention ](https://www.pnas.org/doi/10.1073/pnas.2502599122)”, *Proceedings of the National Academy of Sciences (PNAS)*, vol. 122, no. 28, 2025.





 

 

Y. M. Lu, M. I. Letey, J. A. Zavatone-Veth*, A. Maiti*, and C. Pehlevan,

“[Asymptotic theory of in-context learning by linear attention ](https://www.pnas.org/doi/10.1073/pnas.2502599122)”, *Proceedings of the National Academy of Sciences (PNAS)*, vol. 122, no. 28, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Lu-et-al-PNAS_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Lu-et-al-PNAS_2025.pdf)
 
 

M. Erdogan, C. Pehlevan, and A. T. Erdogan,

“[Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism](https://openreview.net/forum?id=IZ1KYTU9ON)”, *Advances in Neural Information Processing Systems (NeurIPS) (Spotlight), 2025*, 2025.





 

 

M. Erdogan, C. Pehlevan, and A. T. Erdogan,

“[Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism](https://openreview.net/forum?id=IZ1KYTU9ON)”, *Advances in Neural Information Processing Systems (NeurIPS) (Spotlight), 2025*, 2025.





 

 

 

 

J. A. Zavatone-Veth, B. Bordelon, and C. Pehlevan,

“[Summary statistics of learning link changing neural representations to behavior](https://www.frontiersin.org/journals/neural-circuits/articles/10.3389/fncir.2025.1618351/full)”, *Frontiers in Neural Circuits*, vol. 19, 2025.





 

 

J. A. Zavatone-Veth, B. Bordelon, and C. Pehlevan,

“[Summary statistics of learning link changing neural representations to behavior](https://www.frontiersin.org/journals/neural-circuits/articles/10.3389/fncir.2025.1618351/full)”, *Frontiers in Neural Circuits*, vol. 19, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Zavatone-Veth_etal_FiNC_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Zavatone-Veth_etal_FiNC_2025.pdf)
 
 

B. S. Ruben, W. L. Tong, H. T. Chaudhry, and C. Pehlevan,

“[No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions](https://openreview.net/forum?id=z9GgK3CK39)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

B. S. Ruben, W. L. Tong, H. T. Chaudhry, and C. Pehlevan,

“[No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions](https://openreview.net/forum?id=z9GgK3CK39)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Ruben_etal_ICML_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Ruben_etal_ICML_2025.pdf)
 
 

J. A. Zavatone-Veth and C. Pehlevan,

“[Nadaraya-Watson kernel smoothing as a random energy model ](https://iopscience.iop.org/article/10.1088/1742-5468/ada49a)”, *J. Stat. Mech.*, vol. 2025, 2025.





 

 

J. A. Zavatone-Veth and C. Pehlevan,

“[Nadaraya-Watson kernel smoothing as a random energy model ](https://iopscience.iop.org/article/10.1088/1742-5468/ada49a)”, *J. Stat. Mech.*, vol. 2025, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-01/Zavatone-Veth%26Pehlevan_JStatMech_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-01/Zavatone-Veth%26Pehlevan_JStatMech_2025.pdf)
 
 

N. Dey *et al.*,

“[Don’t be lazy: CompleteP enables compute-efficient deep transformers](https://openreview.net/forum?id=lMU2kaMANl)”, *Advances in Neural Information Processing Systems (NeurIPS), 2025*, 2025.





 

 

N. Dey *et al.*,

“[Don’t be lazy: CompleteP enables compute-efficient deep transformers](https://openreview.net/forum?id=lMU2kaMANl)”, *Advances in Neural Information Processing Systems (NeurIPS), 2025*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-02/Dey_etal_NeurIPS_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2026-02/Dey_etal_NeurIPS_2025.pdf)
 
 

A. Atanasov, J. A. Zavatone-Veth, and C. Pehlevan,

“[Risk and cross validation in ridge regression with correlated samples ](https://openreview.net/forum?id=GMwKpJ9TiR)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

A. Atanasov, J. A. Zavatone-Veth, and C. Pehlevan,

“[Risk and cross validation in ridge regression with correlated samples ](https://openreview.net/forum?id=GMwKpJ9TiR)”, *International Conference on Machine Learning (ICML)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Atanasov_etal_ICML_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-06/Atanasov_etal_ICML_2025.pdf)
 
 

A. Meterez, D. Morwani, C.-A. Oncescu, J. Wu, C. Pehlevan, and S. Kakade,

“[A Simplified Analysis of SGD for Linear Regression with Weight Averaging](https://openreview.net/forum?id=8Ha3DygVDz)”, *NeurIPS Workshop OPT 2025: Optimization for Machine Learning*, 2025.





 

 

A. Meterez, D. Morwani, C.-A. Oncescu, J. Wu, C. Pehlevan, and S. Kakade,

“[A Simplified Analysis of SGD for Linear Regression with Weight Averaging](https://openreview.net/forum?id=8Ha3DygVDz)”, *NeurIPS Workshop OPT 2025: Optimization for Machine Learning*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-11/Meterez_OPT_NeurIPS_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-11/Meterez_OPT_NeurIPS_2025.pdf)
 
 

B. Bordelon*, A. Atanasov*, and C. Pehlevan,

“[How Feature Learning Can Improve Neural Scaling Laws](https://openreview.net/forum?id=dEypApI1MZ)”, *International Conference on Learning Representations (ICLR) (Spotlight)*, 2025.





 

 

B. Bordelon*, A. Atanasov*, and C. Pehlevan,

“[How Feature Learning Can Improve Neural Scaling Laws](https://openreview.net/forum?id=dEypApI1MZ)”, *International Conference on Learning Representations (ICLR) (Spotlight)*, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Bordelon_etal_ICLR_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-05/Bordelon_etal_ICLR_2025.pdf)
 
 

B. Bordelon, A. Atanasov, and C. Pehlevan,

“[How feature learning can improve neural scaling laws](https://iopscience.iop.org/article/10.1088/1742-5468/adefb1/meta)”, *Journal of Statistical Mechanics: Theory and Experiment (JSTAT)*, vol. 8, 2025.





 

 

B. Bordelon, A. Atanasov, and C. Pehlevan,

“[How feature learning can improve neural scaling laws](https://iopscience.iop.org/article/10.1088/1742-5468/adefb1/meta)”, *Journal of Statistical Mechanics: Theory and Experiment (JSTAT)*, vol. 8, 2025.





 

 

 

- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Bordelon_etal_JStatMech_2025.pdf)
 
- [ picture\_as\_pdfPDF](/sites/g/files/omnuum6471/files/2025-08/Bordelon_etal_JStatMech_2025.pdf)
 
 

B. Wang and C. Pehlevan,

“[An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models](https://openreview.net/forum?id=SDhOClkyqC)”, *Advances in Neural Information Processing Systems (NeurIPS) (Spotlight)*, 2025.





 

 

B. Wang and C. Pehlevan,

“[An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models](https://openreview.net/forum?id=SDhOClkyqC)”, *Advances in Neural Information Processing Systems (NeurIPS) (Spotlight)*, 2025.





 

 

 

 

 



 

Show morerefresh