Publications

You can also find my articles on Google Scholar

Learning State-Tracking from Code: REPL Traces and Probabilistic Automata Internal page

Julien Siems, Riccardo Grazzi, Kirill Kalinin, Hitesh Ballani, Babak Rahmani

Workshop on Latent & Implicit Thinking – Going Beyond CoT Reasoning (2026)

Debugging code world models Internal page

Babak Rahmani

ICLR 2026 Workshop on Logical Reasoning of Large Language Models (2026)

Workshop on Latent & Implicit Thinking – Going Beyond CoT Reasoning (2026)

Training Deep Physical Neural Networks Internal page

Ali Momeni, Babak Rahmani, Benjamin Scellier, Logan G. Wright, Peter L. McMahon, Clara C. Wanjura, Yuhang Li, Anas Skalli, Natalia G. Berloff, Tatsuhiro Onodera, Ilker Oguz, Francesco Morichetti, Philipp del Hougne, Manuel Le Gallo, Abu Sebastian, Azalia Mirhoseini, Cheng Zhang, Danijela Marković, Daniel Brunner, Christophe Moser, Sylvain Gigan, Florian Marquardt, Aydogan Ozcan, Julie Grollier, Andrea J. Liu, Demetri Psaltis, Andrea Alù, Romain Fleury

Nature (2025)

AOC Internal page

Kirill P. Kalinin, Jannes Gladrow, Jiaqi Chu, James H. Clegg, Daniel Cletheroe, Douglas J. Kelly, Babak Rahmani (co-first author), Grace Brennan, Burcu Canakci, Fabian Falck, Michael Hansen, Jim Kleewein, Heiner Kremer, Greg O’Shea, Lucinda Pickup, Saravan Rajmohan, Ant Rowstron, Victor Ruhle, Lee Braine, Shrirang Khedekar, Natalia G. Berloff, Christos Gkantsidis, Francesca Parmigiani, Hitesh Ballani

Nature (2025)

Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media Internal page

Babak Rahmani, Damien Loterie, Eirini Kakkava, Navid Borhani, Uğur Teğin, Demetri Psaltis, Christophe Moser

Nature Machine Intelligence (2020)

Multimode optical fiber transmission with a deep learning network Internal page

Babak Rahmani, Damien Loterie, Georgia Konstantinou, Demetri Psaltis, Christophe Moser

Nature Light Science and Application (2018)

Babak Rahmani

Publications

Learning State-Tracking from Code: REPL Traces and Probabilistic Automata Internal page

Debugging code world models Internal page

Training Deep Physical Neural Networks Internal page

AOC Internal page

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity Internal page

Regularizing the Infinite: Improved Generalization Performance with Deep Equilibrium Models Internal page

An actor-model framework for visual sensory encoding Internal page

Backpropagation-free Training of Deep Physical Neural Networks Internal page

Natural image synthesis for the retina with variational information bottleneck representation Internal page

Variational framework for partially-measured physical system control Internal page

Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media Internal page

Multimode optical fiber transmission with a deep learning network Internal page