@inproceedings{kim2026inverting,
  title = {Inverting Data Transformations via Diffusion Sampling},
  author = {Kim, Jinwoo and Kaba, S{\'e}kou-Oumar and Park, Jiyun and Hong, Seunghoon and Ravanbakhsh, Siamak},
  booktitle = {Forty-Third International Conference on Machine Learning},
  year = {2026}
}

@inproceedings{ni2026long,
  title = {Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism},
  author = {Ni, Tianwei and Derman, Esther and Jain, Vineet and Taboga, Vincent and Ravanbakhsh, Siamak and Bacon, Pierre-Luc},
  booktitle = {Forty-Third International Conference on Machine Learning},
  year = {2026}
}

@inproceedings{pedramfarmulti,
  title = {Multi-Armed Sampling Problem and the End of Exploration},
  author = {Pedramfar, Mohammad and Ravanbakhsh, Siamak},
  booktitle = {The 29th International Conference on Artificial Intelligence and Statistics},
  year = {2026},
  organization = {PMLR},
  url_arxiv = {https://arxiv.org/abs/2507.10797}
}

@inproceedings{ngo2025scaling,
  title = {Scaling laws and symmetry, evidence from neural force fields},
  author = {Ngo, Khang and Ravanbakhsh, Siamak},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url_arxiv = {https://arxiv.org/abs/2510.09768}
}

@inproceedings{shakerinavaexpressive,
  title = {The Expressive Limits of Diagonal SSMs for State-Tracking},
  author = {Shakerinava, Mehran and Khavari, Behnoush and Ravanbakhsh, Siamak and Chandar, Sarath},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url_arxiv = {https://arxiv.org/abs/2603.01959}
}

@article{shakerinava2026beyond,
  title = {Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs},
  author = {Shakerinava, Mehran and Ravanbakhsh, Siamak and Oberman, Adam},
  journal = {Advances in Neural Information Processing Systems},
  volume = {38},
  pages = {109446--109470},
  year = {2025},
  url_paper = {https://proceedings.neurips.cc/paper_files/paper/2025/file/9dc3ba306fcad7d8ee00eb30a8156c02-Paper-Conference.pdf}
}

@article{jain2026diffusion,
  title = {Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models},
  author = {Jain, Vineet and Sareen, Kusha and Pedramfar, Mohammad and Ravanbakhsh, Siamak},
  journal = {Advances in Neural Information Processing Systems},
  volume = {38},
  pages = {145576--145615},
  year = {2025},
  url_paper = {https://proceedings.neurips.cc/paper_files/paper/2025/file/d6484394c4cb5e1f4ecad8d90b912025-Paper-Conference.pdf}
}

@article{kaba2026energy,
  title = {Energy Loss Functions for Physical Systems},
  author = {Kaba, Oumar and Sareen, Kusha and Levy, Daniel and Ravanbakhsh, Siamak},
  journal = {Advances in Neural Information Processing Systems},
  volume = {38},
  pages = {163916--163947},
  year = {2025},
  url_paper = {https://proceedings.neurips.cc/paper_files/paper/2025/file/efd3901eeda94e200f0634f3a27298b8-Paper-Conference.pdf}
}

@article{li2025identifiability,
  title = {On the Identifiability of Causal Abstractions},
  author = {Li, Xiusi and Kaba, S{\'e}kou-Oumar and Ravanbakhsh, Siamak},
  journal = {The 28th International Conference on Artificial Intelligence and Statistics},
  year = {2025},
  organization = {PMLR},
  url_arxiv = {https://arxiv.org/abs/2503.10834},
  url_paper = {https://openreview.net/attachment?id=RKiOGRrABL&name=pdf}
}

@article{akhound2026progressive,
  title = {Progressive inference-time annealing of diffusion models for sampling from boltzmann densities},
  author = {Akhound-Sadegh, Tara and Lee, Jungyoon and Bose, Joey and De Bortoli, Valentin and Doucet, Arnaud and Bronstein, Michael and Beaini, Dominique and Ravanbakhsh, Siamak and Neklyudov, Kirill and Tong, Alexander},
  journal = {Advances in Neural Information Processing Systems},
  volume = {38},
  pages = {63218--63251},
  year = {2025},
  url_paper = {https://proceedings.neurips.cc/paper_files/paper/2025/file/5b6e19673f5510e00a73326a07363b84-Paper-Conference.pdf}
}

@inproceedings{jainsampling,
  title = {Sampling from Energy-based Policies using Diffusion},
  author = {Jain, Vineet and Akhound-Sadegh, Tara and Ravanbakhsh, Siamak},
  year = {2025},
  booktitle = {Reinforcement Learning Conference},
  url_arxiv = {https://arxiv.org/abs/2410.01312}
}

@inproceedings{levysymmcd,
  title = {SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models},
  author = {Levy, Daniel and Panigrahi, Siba Smarak and Kaba, S{\'e}kou-Oumar and Zhu, Qiang and Lee, Kin Long Kelvin and Galkin, Mikhail and Miret, Santiago and Ravanbakhsh, Siamak},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
  url_paper = {https://openreview.net/pdf?id=xnssGv9rpW},
  url_arxiv = {https://arxiv.org/abs/2502.03638}
}

@inproceedings{trang20243,
  title = {E (3)-Equivariant Mesh Neural Networks},
  author = {Trang, Thuan Anh and Ngo, Nhat Khang and Levy, Daniel T and Vo, Thieu Ngoc and Ravanbakhsh, Siamak and Hy, Truong Son},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  pages = {748--756},
  year = {2024},
  organization = {PMLR},
  url_paper = {https://proceedings.mlr.press/v238/anh-trang24a.html}
}

@inproceedings{mondalefficient,
  title = {Efficient Dynamics Modeling in Interactive Environments with Koopman Theory},
  author = {Mondal, Arnab Kumar and Panigrahi, Siba Smarak and Rajeswar, Sai and Siddiqi, Kaleem and Ravanbakhsh, Siamak},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url_arxiv = {https://arxiv.org/abs/2306.11941},
  url_paper = {https://openreview.net/pdf?id=fkrYDQaHOJ}
}

@inproceedings{akhounditerated,
  title = {Iterated Denoising Energy Matching for Sampling from Boltzmann Densities},
  author = {Akhound-Sadegh, Tara and Rector-Brooks, Jarrid and Bose, Joey and Mittal, Sarthak and Lemos, Pablo and Liu, Cheng-Hao and Sendera, Marcin and Ravanbakhsh, Siamak and Gidel, Gauthier and Bengio, Yoshua and others},
  booktitle = {Forty-first International Conference on Machine Learning},
  year = {2024},
  url_paper = {https://openreview.net/pdf?id=gVjMwLDFoQ},
  url_arxiv = {https://arxiv.org/abs/2402.06121}
}

@inproceedings{jainlearning,
  title = {Learning to Reach Goals via Diffusion},
  author = {Jain, Vineet and Ravanbakhsh, Siamak},
  booktitle = {Forty-first International Conference on Machine Learning},
  year = {2024},
  url_paper = {https://openreview.net/pdf?id=3JhmHCVPa8},
  url_arxiv = {https://arxiv.org/abs/2310.02505}
}

@inproceedings{livernochediffusion,
  title = {On Diffusion Modeling for Anomaly Detection},
  author = {Livernoche, Victor and Jain, Vineet and Hezaveh, Yashar and Ravanbakhsh, Siamak},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url_paper = {https://openreview.net/pdf?id=lR3rk7ysXz},
  url_arxiv = {https://arxiv.org/abs/2305.18593}
}

@inproceedings{shakerinava2024weight,
  title = {Weight-Sharing Regularization},
  author = {Shakerinava, Mehran and Sohrabi, Motahareh MS and Ravanbakhsh, Siamak and Lacoste-Julien, Simon},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  pages = {4204--4212},
  year = {2024},
  organization = {PMLR},
  url_paper = {https://proceedings.mlr.press/v238/shakerinava24a.html},
  url_arxiv = {https://arxiv.org/abs/2311.03096}
}

@inproceedings{pmlr-v202-kaba23a,
  title = {Equivariance with Learned Canonicalization Functions},
  author = {Kaba, S\'{e}kou-Oumar and Mondal, Arnab Kumar and Zhang, Yan and Bengio, Yoshua and Ravanbakhsh, Siamak},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  pages = {15546--15566},
  year = {2023},
  editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
  volume = {202},
  series = {Proceedings of Machine Learning Research},
  month = {23--29 Jul},
  publisher = {PMLR},
  url_pdf = {https://proceedings.mlr.press/v202/kaba23a/kaba23a.pdf},
  url = {https://proceedings.mlr.press/v202/kaba23a.html}
}

@inproceedings{mondal2023equivariant,
  title = {Equivariant Adaptation of Large Pretrained Models},
  author = {Mondal, Arnab Kumar and Panigrahi, Siba Smarak and Kaba, S{\'e}kou-Oumar and Rajeswar, Sai and Ravanbakhsh, Siamak},
  booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
  year = {2023},
  url_pdf = {https://arxiv.org/abs/2310.01647}
}

@inproceedings{akhound2023lieneurips,
  title = {Lie Point Symmetry and Physics Informed Networks},
  author = {Akhound-Sadegh, Tara and Perreault-Levasseur, Laurence and Brandstetter, Johannes and Welling, Max and Ravanbakhsh, Siamak},
  booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
  year = {2023},
  url_pdf = {https://arxiv.org/abs/2311.04293}
}

@inproceedings{mondal2022eqr,
  title = {EqR: Equivariant Representations for Data-Efficient Reinforcement Learning},
  author = {Mondal, Arnab Kumar and Jain, Vineet and Siddiqi, Kaleem and Ravanbakhsh, Siamak},
  booktitle = {International Conference on Machine Learning},
  pages = {15908--15926},
  year = {2022},
  organization = {PMLR},
  url_pdf = {https://proceedings.mlr.press/v162/mondal22a/mondal22a.pdf},
  url_code = {https://github.com/arnab39/Symmetry-RL}
}

@inproceedings{NEURIPS2022_1abed6ee,
  author = {Kaba, Oumar and Ravanbakhsh, Siamak},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
  pages = {4150--4164},
  publisher = {Curran Associates, Inc.},
  title = {Equivariant Networks for Crystal Structures},
  url_pdf = {https://proceedings.neurips.cc/paper_files/paper/2022/file/1abed6ee581b9ceb4e2ddf37822c7fcb-Paper-Conference.pdf},
  volume = {35},
  year = {2022}
}

@inproceedings{pmlr-v162-morris22a,
  title = {{S}peq{N}ets: Sparsity-aware permutation-equivariant graph networks},
  author = {Morris, Christopher and Rattan, Gaurav and Kiefer, Sandra and Ravanbakhsh, Siamak},
  booktitle = {Proceedings of the 39th International Conference on Machine Learning},
  pages = {16017--16042},
  year = {2022},
  editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = {162},
  series = {Proceedings of Machine Learning Research},
  month = {17--23 Jul},
  publisher = {PMLR},
  url_pdf = {https://proceedings.mlr.press/v162/morris22a/morris22a.pdf}
}

@inproceedings{NEURIPS2022_dcd29769,
  author = {Shakerinava, Mehran and Mondal, Arnab Kumar and Ravanbakhsh, Siamak},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
  pages = {34162--34174},
  publisher = {Curran Associates, Inc.},
  title = {Structuring Representations Using Group Invariants},
  url_pdf = {https://proceedings.neurips.cc/paper_files/paper/2022/file/dcd297696d0bb304ba426b3c5a679c37-Paper-Conference.pdf},
  volume = {35},
  year = {2022}
}

@inproceedings{shakerinava2022utility,
  title = {Utility Theory for Sequential Decision Making},
  author = {Shakerinava, Mehran and Ravanbakhsh, Siamak},
  booktitle = {International Conference on Machine Learning},
  pages = {19616--19625},
  year = {2022},
  organization = {PMLR},
  url_pdf = {https://proceedings.mlr.press/v162/shakerinava22a/shakerinava22a.pdf}
}

@inproceedings{pmlr-v139-shakerinava21a,
  title = {Equivariant Networks for Pixelized Spheres},
  author = {Shakerinava, Mehran and Ravanbakhsh, Siamak},
  booktitle = {Proceedings of the 38th International Conference on Machine Learning},
  pages = {9477--9488},
  year = {2021},
  editor = {Meila, Marina and Zhang, Tong},
  volume = {139},
  series = {Proceedings of Machine Learning Research},
  month = {18--24 Jul},
  publisher = {PMLR},
  url_pdf = {http://proceedings.mlr.press/v139/shakerinava21a/shakerinava21a.pdf},
  url_code = {https://github.com/mshakerinava/Equivariant-Networks-for-Pixelized-Spheres}
}

@inproceedings{wang2020equivariant,
  author = {Wang, Renhao and Albooyeh, Marjan and Ravanbakhsh, Siamak},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},
  pages = {13806--13817},
  publisher = {Curran Associates, Inc.},
  title = {Equivariant Networks for Hierarchical Structures},
  url_pdf = {https://proceedings.neurips.cc/paper/2020/file/9efb1a59d7b58e69996cf0e32cb71098-Paper.pdf},
  url_arxiv = {http://proceedings.mlr.press/v119/ravanbakhsh20a/ravanbakhsh20a.pdf},
  url_code = {https://github.com/rw435/wreathProdNet},
  volume = {33},
  year = {2020}
}

@inproceedings{pmlr-v119-ravanbakhsh20a,
  title = {Universal Equivariant Multilayer Perceptrons},
  author = {Ravanbakhsh, Siamak},
  booktitle = {Proceedings of the 37th International Conference on Machine Learning},
  pages = {7996--8006},
  year = {2020},
  editor = {Hal Daumé III and Aarti Singh},
  volume = {119},
  series = {Proceedings of Machine Learning Research},
  address = {Virtual},
  month = {13--18 Jul},
  publisher = {PMLR},
  url_pdf = {http://proceedings.mlr.press/v119/ravanbakhsh20a/ravanbakhsh20a.pdf},
  url_paper = {http://proceedings.mlr.press/v119/ravanbakhsh20a.html}
}

@inproceedings{fatemi2019improved,
  title = {Improved knowledge graph embedding using background taxonomic information},
  author = {Fatemi, Bahare and Ravanbakhsh, Siamak and Poole, David},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {33},
  pages = {3526--3533},
  year = {2019}
}

@inproceedings{pmlr-v80-hartford18a,
  title = {Deep Models of Interactions Across Sets},
  author = {Hartford, Jason and Graham, Devon and Leyton-Brown, Kevin and Ravanbakhsh, Siamak},
  booktitle = {Proceedings of the 35th International Conference on Machine Learning},
  pages = {1909--1918},
  year = {2018},
  volume = {80},
  series = {Proceedings of Machine Learning Research},
  month = {Jul},
  publisher = {PMLR},
  url_pdf = {http://proceedings.mlr.press/v80/hartford18a/hartford18a-supp.pdf},
  url_arxiv = {https://arxiv.org/abs/1803.02879}
}

@inproceedings{singla2018subject2vec,
  title = {Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector},
  author = {Singla, Sumedha and Gong, Mingming and Ravanbakhsh, Siamak and Sciurba, Frank and Poczos, Barnabas and Batmanghelich, Kayhan N},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages = {502--510},
  year = {2018},
  organization = {Springer}
}

@inproceedings{NIPS2017_6931,
  title = {Deep Sets},
  author = {Zaheer, Manzil and Kottur, Satwik and Ravanbakhsh, Siamak and Poczos, Barnabas and Salakhutdinov, Ruslan R and Smola, Alexander J},
  booktitle = {Advances in Neural Information Processing Systems 30},
  pages = {3391--3401},
  year = {2017},
  publisher = {Curran Associates, Inc.},
  url_pdf = {http://papers.nips.cc/paper/6931-deep-sets.pdf},
  url_arxiv = {https://arxiv.org/abs/1703.06114},
  url_code = {https://github.com/manzilzaheer/DeepSets}
}

@inproceedings{ravanbakhsh_gengalaxy,
  title = {Enabling Dark Energy Science with Deep Generative Models of Galaxy Images},
  author = {Ravanbakhsh, Siamak and Lanusse, Francois and Mandelbaum, Rachel and Schneider, Jeff and Poczos, Barnabas},
  booktitle = {Proceedings of the Thirty First AAAI Conference on Artificial Intelligence},
  url_arxiv = {https://arxiv.org/abs/1609.05796},
  url_pdf = {http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14765/13939},
  year = {2017}
}

@inproceedings{ravanbakhsh_equivariance,
  author = {Ravanbakhsh, Siamak and Schneider, Jeff and Poczos, Barnabas},
  title = {Equivariance Through Parameter-Sharing},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning},
  series = {JMLR: W&CP},
  volume = {70},
  year = {2017},
  month = {August},
  url_arxiv = {https://arxiv.org/abs/1702.08389},
  url_pdf = {http://proceedings.mlr.press/v70/ravanbakhsh17a/ravanbakhsh17a-supp.pdf}
}

@inproceedings{NIPS2017_7140,
  title = {Min-Max Propagation},
  author = {Srinivasa, Christopher and Givoni, Inmar and Ravanbakhsh, Siamak and Frey, Brendan J},
  booktitle = {Advances in Neural Information Processing Systems 30},
  pages = {5565--5573},
  year = {2017},
  publisher = {Curran Associates, Inc.},
  url_pdf = {http://papers.nips.cc/paper/7140-min-max-propagation.pdf}
}

@inproceedings{ravanbakhsh_boolean,
  title = {Boolean Matrix Factorization and Noisy Completion via Message Passing},
  author = {Ravanbakhsh, Siamak and P{\'o}czos, Barnab{\'a}s and Greiner, Russell},
  booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
  series = {JMLR: W&CP},
  volume = {48},
  year = {2016},
  url_paper = {http://jmlr.org/proceedings/papers/v48/ravanbakhsha16.pdf},
  url_code = {https://github.com/mravanba/BooleanFactorization}
}

@inproceedings{ravanbakhsh_lambdacdm,
  title = {Estimating Cosmological Parameters from the Dark Matter Distribution},
  author = {Ravanbakhsh, Siamak and Oliva, Junier and Fromenteau, Sebastien and Price, Layne C and Ho, Shirley and Schneider, Jeff and P{\'o}czos, Barnab{\'a}s},
  booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
  editor = {Maria Balcan and Kilian Weinberger},
  series = {JMLR: W&CP},
  volume = {48},
  year = {2016},
  url_paper = {http://jmlr.org/proceedings/papers/v48/ravanbakhshb16.pdf}
}

@inproceedings{ravanbakhsh_exprbm,
  author = {Ravanbakhsh, Siamak and Poczos, Barnabas and Schneider, Jeff and Schuurmans, Dale and Greiner, Russell},
  title = {Stochastic Neural Networks with Monotonic Activation Functions},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  series = {JMLR: W&CP},
  volume = {51},
  pages = {809–818},
  year = {2016},
  url_pdf = {http://www.jmlr.org/proceedings/papers/v51/ravanbakhsh16.pdf}
}

@inproceedings{Srinivasa_sp,
  author = {Srinivasa, Christopher and Ravanbakhsh, Siamak and Frey, Brendan},
  title = {Survey Propagation beyond Constraint Satisfaction Problems},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  series = {JMLR: W&CP},
  volume = {51},
  pages = {286–295},
  year = {2016},
  url_pdf = {http://www.jmlr.org/proceedings/papers/v51/srinivasa16.pdf}
}

@incollection{NIPS2015_5675,
  title = {Embedding Inference for Structured Multilabel Prediction},
  author = {Mirzazadeh, Farzaneh and Ravanbakhsh, Siamak and Ding, Nan and Schuurmans, Dale},
  booktitle = {Advances in Neural Information Processing Systems 28},
  editor = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  pages = {3555--3563},
  year = {2015},
  publisher = {Curran Associates, Inc.},
  url_pdf = {http://papers.nips.cc/paper/5675-embedding-inference-for-structured-multilabel-prediction.pdf}
}

@inproceedings{ravanbakhsh_tsp,
  author = {Ravanbakhsh, Siamak and Rabbany, Reihaneh and Greiner, Russell},
  title = {Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2014},
  pages = {289--297},
  publisher = {MIT Press},
  address = {Cambridge, MA, USA},
  url_paper = {https://papers.nips.cc/paper/5601-augmentative-message-passing-for-traveling-salesman-problem-and-graph-partitioning.pdf}
}

@inproceedings{ravanbakhsh_minmax,
  title = {Min-Max Problems on Factor Graphs},
  author = {Ravanbakhsh, Siamak and Srinivasa, Christopher and Frey, Brendan and Greiner, Russell},
  booktitle = {Proceedings of the 31st International Conference on Machine Learning},
  pages = {1035--1043},
  year = {2014},
  url_pdf = {http://jmlr.org/proceedings/papers/v32/ravanbakhsh14.pdf}
}

@inproceedings{ravanbakhsh_glc,
  author = {Siamak Ravanbakhsh and Chun-Nam Yu and Russell Greiner},
  title = {A Generalized Loop Correction Method for Approximate Inference in Graphical Models},
  booktitle = {Proceedings of the 29th International Conference on Machine Learning},
  series = {ICML '12},
  year = {2012},
  editor = {John Langford and Joelle Pineau},
  month = {July},
  publisher = {Omnipress},
  address = {New York, NY, USA},
  pages = {543--550},
  url_pdf = {http://icml.cc/2012/papers/304.pdf}
}

@inproceedings{ravanbakhsh_nmr,
  author = {Ravanbakhsh, Siamak and Poczos, Barnabas and Greiner, Russ},
  title = {A Cross Entropy Optimization Method for Partially Decomposable Problems},
  booktitle = {Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. Special Track on AI and Bioinformatics},
  pages = {1280--1286},
  year = {2010},
  editor = {M. Fox, D. Poole},
  publisher = {AAAI Press},
  month = {July 11 {--} 15},
  address = {Atlanta, USA},
  url_paper = {http://www.aaai.org/ocs/index.php/AAAI/AAAI10/paper/view/1848/2196}
}

@article{trang2024scalable,
  title = {Scalable Hierarchical Self-Attention with Learnable Hierarchy for Long-Range Interactions},
  author = {Trang, Thuan and Ngo, Khang Nhat and Sonnery, Hugo and Vo, Thieu and Ravanbakhsh, Siamak and Hy, Truong Son},
  journal = {Transactions on Machine Learning Research},
  year = {2024},
  url_paper = {https://openreview.net/pdf?id=qH4YFMyhce}
}

@article{pagano2023inpaint,
  title = {Characterization of Inpaint Residuals in Interferometric Measurements of the Epoch of Reionization},
  author = {Pagano, Michael and Liu, Jing and Liu, Adrian and Kern, Nicholas S. and Ewall-Wice, Aaron and Bull, Philip and Pascua, Robert and Ravanbakhsh, Siamak and Abdurashidova, Zara and Adams, Tyrone and Aguirre, James E. and others},
  journal = {Monthly Notices of the Royal Astronomical Society},
  year = {2023}
}

@article{jagvaral2022galaxies,
  title = {Galaxies and Halos on Graph Neural Networks: Deep Generative Modeling Scalar and Vector Quantities for Intrinsic Alignment},
  author = {Jagvaral, Yesukhei and Lanusse, Fran{\c{c}}ois and Singh, Sukhdeep and Mandelbaum, Rachel and Ravanbakhsh, Siamak and Campbell, Duncan},
  journal = {Monthly Notices of the Royal Astronomical Society},
  year = {2022},
  url_arxiv = {https://arxiv.org/abs/2204.07077}
}

@article{lanusse2021deep,
  title = {Deep generative models for galaxy image simulations},
  author = {Lanusse, Fran{\c{c}}ois and Mandelbaum, Rachel and Ravanbakhsh, Siamak and Li, Chun-Liang and Freeman, Peter and P{\'o}czos, Barnab{\'a}s},
  journal = {Monthly Notices of the Royal Astronomical Society},
  volume = {504},
  number = {4},
  pages = {5543--5555},
  year = {2021},
  publisher = {Oxford University Press}
}

@article{gagnon2021recovering,
  title = {Recovering the wedge modes lost to 21-cm foregrounds},
  author = {Gagnon-Hartman, Samuel and Cui, Yue and Liu, Adrian and Ravanbakhsh, Siamak},
  journal = {Monthly Notices of the Royal Astronomical Society},
  volume = {504},
  number = {4},
  pages = {4716--4729},
  year = {2021},
  publisher = {Oxford University Press}
}

@article{he2019learning,
  title = {Learning to predict the cosmological structure formation},
  author = {He, Siyu and Li, Yin and Feng, Yu and Ho, Shirley and Ravanbakhsh, Siamak and Chen, Wei and Poczos, Barnabas},
  journal = {Proceedings of the National Academy of Sciences},
  pages = {201821458},
  year = {2019},
  publisher = {National Acad Sciences}
}

@article{doi:10.1093/mnras/stx1665,
  author = {Lanusse, François and Ma, Quanbin and Li, Nan and Collett, Thomas E. and Li, Chun-Liang and Ravanbakhsh, Siamak and Mandelbaum, Rachel and Póczos, Barnabás},
  title = {CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding},
  journal = {Monthly Notices of the Royal Astronomical Society},
  volume = {473},
  number = {3},
  pages = {3895-3906},
  year = {2018},
  doi = {10.1093/mnras/stx1665},
  url = {http://dx.doi.org/10.1093/mnras/stx1665},
  url_code = {https://github.com/McWilliamsCenter/CMUDeepLens},
  url_arxiv = {https://arxiv.org/abs/1703.02642}
}

@article{tomczak2018low,
  title = {Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines},
  author = {Tomczak, Jakub M and Zar{\k{e}}ba, Szymon and Ravanbakhsh, Siamak and Greiner, Russell},
  journal = {Neural Processing Letters},
  pages = {1--19},
  year = {2018},
  publisher = {Springer}
}

@article{ravanbakhsh_plosone,
  author = {Ravanbakhsh, Siamak and Liu, Philip and Bjordahl, Trent and Mandal, Rupasri and Grant, Jason and Wilson, Michael and Eisner, Roman and Sinelnikov, Igor and Hu, Xiaoyu and Luchinat, Claudio and Greiner, Russell and Wishart, David},
  journal = {PLoS ONE},
  publisher = {Public Library of Science},
  title = {Accurate, Fully-Automated NMR Spectral Profiling for Metabolomics},
  year = {2015},
  month = {05},
  volume = {10},
  pages = {e0124219},
  number = {5},
  doi = {10.1371/journal.pone.0124219},
  url_arxiv = {https://arxiv.org/abs/1409.1456},
  url_pdf = {http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0124219}
}

@article{ravanbakhsh_csp,
  title = {Perturbed Message Passing for Constraint Satisfaction Problems},
  author = {Ravanbakhsh, Siamak and Greiner, Russell},
  journal = {Journal of Machine Learning Research},
  volume = {16},
  pages = {1249-1274},
  year = {2015},
  url_pdf = {http://www.jmlr.org/papers/volume16/ravanbakhsh15a/ravanbakhsh15a.pdf}
}

@article{ravanbakhsh_tubulin,
  title = {Determination of the optimal tubulin isotype target as a method for the development of individualized cancer chemotherapy},
  author = {Ravanbakhsh, Siamak and Gajewski, Melissa and Greiner, Russell and Tuszynski, Jack A},
  journal = {Theoretical Biology and Medical Modelling},
  volume = {10},
  number = {1},
  pages = {1},
  year = {2013},
  publisher = {BioMed Central},
  url_pdf = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3651705/pdf/1742-4682-10-29.pdf}
}

@inproceedings{zhang2026molecule,
  title = {Molecule property prediction with molecular orbitals},
  author = {Zhang, Yan and Ngo, Khang and Kaba, S{\'e}kou-Oumar and Levy, Daniel T and Ravanbakhsh, Siamak and Baratin, Aristide and Kwon, Kisoo and Jang, MiYoung and Cho, Eun Hyun and Park, Sangha and others},
  booktitle = {ICLR Workshop on AI for Accelerated Materials Design (AI4MAT)},
  year = {2026}
}

@inproceedings{jain2025tta,
  title = {Diffusion Tree Sampling: Scalable Inference-Time Alignment of Diffusion Models},
  author = {Jain, Vineet and Sareen, Kusha and Pedramfar, Mohammad and Ravanbakhsh, Siamak},
  booktitle = {ICML Workshop on Test-Time Adaptation},
  year = {2025}
}

@inproceedings{ni2025long,
  title = {Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism},
  author = {Ni, Tianwei and Derman, Esther and Jain, Vineet and Taboga, Vincent and Ravanbakhsh, Siamak and Bacon, Pierre-Luc},
  booktitle = {NeurIPS 2025 Workshop: Second Workshop on Aligning Reinforcement Learning Experimentalists and Theorists},
  year = {2025},
  url_paper = {https://openreview.net/pdf?id=iDGX01XFuK}
}

@inproceedings{khavari2025parity,
  title = {Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMs},
  author = {Khavari, Behnoush and Khullar, Jayesh and Shakerinava, Mehran and Huang, Jerry and Ravanbakhsh, Siamak and Chandar, Sarath},
  booktitle = {ICML 2025 Workshop on Methods and Opportunities at Small Scale},
  url_arxiv = {https://arxiv.org/abs/2508.07395},
  year = {2025}
}

@inproceedings{akhound2025genbio,
  title = {Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities},
  author = {Akhound-Sadegh, Tara and Lee, Jungyoon and Bose, Joey and De Bortoli, Valentin and Doucet, Arnaud and Bronstein, Michael and Beaini, Dominique and Ravanbakhsh, Siamak and Neklyudov, Kirill and Tong, Alexander},
  booktitle = {ICML Workshop on Generative AI and Biology (GenBio)},
  year = {2025}
}

@inproceedings{jain2025gmrl_sampling,
  title = {Sampling from Energy-based Policies using Diffusion},
  author = {Jain, Vineet and Akhound-Sadegh, Tara and Ravanbakhsh, Siamak},
  booktitle = {ICLR Workshop on Generative Models for Robot Learning},
  year = {2025}
}

@inproceedings{sareen2024symmetry,
  title = {Symmetry-Aware Generative Modeling through Learned Canonicalization},
  author = {Sareen, Kusha and Levy, Daniel and Mondal, Arnab Kumar and Kaba, S{\'e}kou-Oumar and Akhound-Sadegh, Tara and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS 2024 Workshop on Symmetry and Geometry in Neural Representations},
  year = {2025},
  url_arxiv = {https://arxiv.org/abs/2501.07773}
}

@inproceedings{shakerinava2025wmw,
  title = {The Expressive Limits of Diagonal SSMs for State-Tracking},
  author = {Shakerinava, Mehran and Khavari, Behnoush and Ravanbakhsh, Siamak and Chandar, Sarath},
  booktitle = {World Modeling Workshop (WMW)},
  year = {2025}
}

@inproceedings{masoud2024diffusion,
  title = {Diffusion-Based In-painting of Corrupted Spectrogram},
  author = {Masoud, Mahsa and Askari, Reyhane and Chen, Kevin and Liu, Adrian and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS Workshop on Machine Learning and the Physical Sciences (also at MAIS and WiML)},
  year = {2024}
}

@inproceedings{mondal2024equiadapt_ws,
  title = {EquiAdapt: Equivariant Adaptation of Large Pretrained Models},
  author = {Mondal, Arnab Kumar and Panigrahi, Siba Smarak and Kaba, S{\'e}kou-Oumar and Rajeswar, Sai and Ravanbakhsh, Siamak},
  booktitle = {CVPR Workshop on Equivariant Vision},
  year = {2024}
}

@inproceedings{jain2024gmrl_goals,
  title = {Learning to Reach Goals via Diffusion},
  author = {Jain, Vineet and Ravanbakhsh, Siamak},
  booktitle = {ICLR Workshop on Generative Models for Decision Making},
  year = {2024}
}

@inproceedings{levy2024symmcd_workshop,
  title = {SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models},
  author = {Levy, Daniel and Panigrahi, Siba Smarak and Kaba, S{\'e}kou-Oumar and Zhu, Qiang and Galkin, Mikhail and Miret, Santiago and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS Workshop on AI for Materials (AI4MAT)},
  year = {2024}
}

@inproceedings{kaba2023symmetry,
  title = {Symmetry Breaking and Equivariant Neural Networks},
  author = {Kaba, S{\'e}kou-Oumar and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations},
  year = {2024},
  url_paper = {https://openreview.net/pdf?id=d55JaRL9wh}
}

@article{mondal2023efficient,
  title = {Efficient Dynamics Modeling in Interactive Environments with Koopman Theory},
  author = {Mondal, Arnab Kumar and Panigrahi, Siba Smarak and Rajeswar, Sai and Siddiqi, Kaleem and Ravanbakhsh, Siamak},
  journal = {European Workshop on Reinforcement Learning},
  url_arxiv = {https://arxiv.org/abs/2306.11941},
  year = {2023}
}

@article{akhound2023lie,
  title = {Lie Point Symmetry and Physics Informed Networks},
  author = {Akhound-Sadegh, Tara and Perreault-Levasseur, Laurence and Brandstetter, Johannes and Welling, Max and Ravanbakhsh, Siamak},
  booktitle = {ICML Workshop on Topology, Algebra and Geometry in Machine Learning},
  url_pdf = {https://openreview.net/pdf?id=VlUf77e9cR},
  year = {2023}
}

@article{dos2023lie,
  title = {Physics-Informed Transformer Networks},
  author = {Dos Santos, Fabricio and Akhound-Sadegh, Tara and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS Workshop on The Symbiosis of Deep Learning and Differential Equations III},
  url_pdf = {https://openreview.net/forum?id=zu80h9YryU},
  year = {2023}
}

@inproceedings{sonnery2023sequoia,
  title = {Sequoia: Hierarchical Self-Attention Layer with Sparse Updates for Point Clouds and Long Sequences},
  author = {Sonnery, Hugo and Trang, Thuan Anh and Thieu, Nhat and Ravanbakhsh, Siamak and Hy, Truong Son},
  booktitle = {ICLR 2023 Workshop on Sparsity in Neural Networks},
  year = {2023}
}

@inproceedings{levy-icml2023,
  title = {Using Multiple Vector Channels Improves E (n)-Equivariant Graph Neural Networks},
  author = {Levy, Daniel and Kaba, Sékou-Oumar and Gonzales, Carmelo and Miret, Santiago and Ravanbakhsh, Siamak},
  booktitle = {ICML Workshop on Machine Learning for Astrophysics},
  url_pdf = {https://ml4astro.github.io/icml2023/assets/68.pdf},
  year = {2023}
}

@inproceedings{kaba2022canonicalization_ws,
  title = {Equivariance with Learned Canonicalization Functions},
  author = {Kaba, S{\'e}kou-Oumar and Mondal, Arnab Kumar and Bengio, Yoshua and Zhang, Yan and Ravanbakhsh, Siamak},
  booktitle = {NeurIPS Workshop on Symmetry and Geometry in Neural Representations},
  year = {2022}
}

@inproceedings{jagvaral2022_workshop,
  title = {Galaxies and Halos on Graph Neural Networks: Deep Generative Modeling Scalar and Vector Quantities for Intrinsic Alignment},
  author = {Jagvaral, Yesukhei and Lanusse, Fran{\c{c}}ois and Singh, Sukhdeep and Mandelbaum, Rachel and Ravanbakhsh, Siamak and Campbell, Duncan},
  booktitle = {ICML Workshop on Machine Learning for Astrophysics},
  year = {2022}
}

@inproceedings{morris2022_workshop,
  title = {SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks},
  author = {Morris, Christopher and Rattan, Gaurav and Kiefer, Sandra and Ravanbakhsh, Siamak},
  booktitle = {ICLR Workshop on Geometrical and Topological Representation Learning},
  year = {2022}
}

@inproceedings{burns2020turbulence,
  title = {Designing Networks to Accurately Learn 2D Turbulence Closures},
  author = {Burns, Keaton and Legin, Ronan and Liu, Adrian and Perreault-Levasseur, Laurence and Hezaveh, Yashar and Ravanbakhsh, Siamak and Wagner, Geoffrey},
  booktitle = {Bulletin of the American Physical Society},
  year = {2020}
}

@inproceedings{he_cmb,
  title = {Analysis of Cosmic Microwave Background with Deep Learning},
  author = {He, Siyu and Ravanbakhsh, Siamak and Ho, Shirley},
  booktitle = {International Conference on Learning Representations (ICLR), workshop track},
  year = {2018},
  url_pdf = {https://openreview.net/pdf?id=B15uoOyvz}
}

@inproceedings{lanusse2018basp,
  title = {Deep Generative Models on Graphs for Emulating Galaxy Alignments in Cosmological Simulations},
  author = {Lanusse, Fran{\c{c}}ois and Ravanbakhsh, Siamak and Mandelbaum, Rachel and P{\'o}czos, Barnab{\'a}s},
  booktitle = {International Biomedical and Astronomical Signal Processing (BASP) Frontiers Workshop},
  year = {2018}
}

@inproceedings{lanusse2017aas,
  title = {Deep Generative Models of Galaxy Images for the Calibration of the Next Generation of Weak Lensing Surveys},
  author = {Lanusse, Fran{\c{c}}ois and Ravanbakhsh, Siamak and P{\'o}czos, Barnab{\'a}s and Schneider, Jeff and Mandelbaum, Rachel},
  booktitle = {229th American Astronomical Society Annual Meeting},
  year = {2017}
}

@inproceedings{ravanbakhsh_sets,
  title = {Deep Learning with Sets and Point Clouds},
  author = {Ravanbakhsh, Siamak and Schneider, Jeff and Poczos, Barnabas},
  booktitle = {International Conference on Learning Representations (ICLR), workshop track},
  year = {2017},
  url_arxiv = {https://arxiv.org/abs/1611.04500},
  url_code = {https://github.com/manzilzaheer/DeepSets}
}

@inproceedings{welle2016soil,
  title = {Leveraging Machine Learning to Estimate Soil Salinity through Satellite-Based Remote Sensing},
  author = {Welle, Paul and Ravanbakhsh, Siamak and P{\'o}czos, Barnab{\'a}s and Mauter, Meagan},
  booktitle = {American Geophysical Union Annual Meeting},
  year = {2016}
}

@inproceedings{ravanbakhsh_pmrbm,
  title = {Training Restricted Boltzmann Machine by Perturbation},
  author = {Ravanbakhsh, Siamak and Greiner, Russell and Frey, Brendan},
  booktitle = {NIPS:workshop on perturbation, optimization and statistics},
  url_pdf = {https://arxiv.org/pdf/1405.1436v1.pdf},
  year = {2014}
}

@inproceedings{ravanbakhsh2010ceed_workshop,
  title = {Benchmarking Cross Entropy Optimization Method: Analysis of a Batch Sampling Method for Large-Scale Structured Optimization},
  author = {Ravanbakhsh, Siamak and Greiner, Russell},
  booktitle = {NeurIPS Workshop on Monte Carlo Methods for Bayesian Inference},
  year = {2010}
}

@article{nitchi_bayesian_last_layer,
  title = {Bayesian Last Layer for Neural Force Fields},
  author = {Nitchi, David and Levy, Daniel and Cote, Michel and Ravanbakhsh, Siamak},
  journal = {Preprint, under review},
  year = {2026}
}

@article{levy_diffusion_tree_search,
  title = {Diffusion Tree Search for Inference Time Adaptation of Material Foundation Models},
  author = {Levy, Daniel and Jain, Vineet and Akhound-Sadegh, Tara and Kaba, S{\'e}kou-Oumar and Ravanbakhsh, Siamak},
  journal = {Preprint, under review},
  year = {2026}
}

@article{sareen_role_of_symmetry,
  title = {The Role of Symmetry in Optimizing Overparameterized Networks},
  author = {Sareen, Kusha and Pedramfar, Mohammad and Shakerinava, Mehran and Kaba, S{\'e}kou-Oumar and Ravanbakhsh, Siamak},
  journal = {Preprint, under review},
  year = {2026}
}

@article{pedramfar_tilted,
  title = {The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret},
  author = {Pedramfar, Mohammad and Ravanbakhsh, Siamak},
  journal = {Preprint, under review},
  year = {2026}
}

@techreport{levy2021heterogenous,
  title = {Equivariant Heterogenous Graph Networks},
  author = {Levy, Daniel and Ravanbakhsh, Siamak},
  year = {2021}
}

@article{lanusse2020deep,
  title = {Deep Generative Models for Galaxy Image Simulations},
  author = {Lanusse, Francois and Mandelbaum, Rachel and Ravanbakhsh, Siamak and Li, Chun-Liang and Freeman, Peter and Poczos, Barnabas},
  journal = {arXiv preprint arXiv:2008.03833},
  year = {2020}
}

@article{graham2020deep,
  title = {Equivariant Entity-Relationship Networks},
  author = {Graham, Devon and Wang, Junhao and Ravanbakhsh, Siamak},
  journal = {arXiv preprint arXiv:1903.09033},
  url_arxiv = {https://arxiv.org/abs/1903.09033},
  url_code = {https://github.com/drgrhm/exch_model},
  year = {2020}
}

@article{albooyeh2019incidence,
  title = {Incidence Networks for Geometric Deep Learning},
  author = {Albooyeh, Marjan and Bertolini, Daniele and Ravanbakhsh, Siamak},
  journal = {arXiv preprint arXiv:1905.11460},
  url_arxiv = {https://arxiv.org/abs/1905.11460},
  year = {2020}
}

@article{venn2019lrp2020,
  title = {LRP2020: Machine Learning Advantages in Canadian Astrophysics},
  author = {Venn, KA and Fabbro, S and Liu, A and Hezaveh, Y and Levasseur, L and Eadie, G and Ellison, S and Woo, J and Kavelaars, JJ and Yi, KM and others},
  journal = {arXiv preprint arXiv:1910.00774},
  year = {2019}
}

@article{li2016annealing,
  title = {Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM},
  author = {Li, Chun-Liang and Ravanbakhsh, Siamak and P{\'o}czos, Barnab{\'a}s},
  journal = {arXiv preprint arXiv:1611.03879},
  year = {2016},
  url_arxiv = {https://arxiv.org/abs/1611.03879}
}

@article{ravanbakhsh2014revisiting,
  title = {Revisiting Algebra and Complexity of Inference in Graphical Models},
  author = {Ravanbakhsh, Siamak and Greiner, Russell},
  journal = {arXiv preprint arXiv:1409.7410},
  year = {2014},
  url_arxiv = {https://arxiv.org/abs/1409.7410}
}

@phdthesis{ravanbakhsh_thesis,
  author = {Siamak Ravanbakhsh},
  title = {Message passing and Combinatorial Optimization},
  school = {University of Alberta},
  address = {Edmonton, AB, Canada},
  year = {2015},
  url_arxiv = {https://cs.ubc.ca/~siamakx/papers/phd_thesis_siamak_ravanbakhsh.pdf},
  url_pdf = {papers/phd_thesis_siamak_ravanbakhsh.pdf}
}

@mastersthesis{ravanbakhsh:thesis,
  author = {Siamak Ravanbakhsh},
  title = {A Stochastic Optimization Method for Partially Decomposable Problems, with Applications to Analysis of NMR Spectra},
  school = {University of Alberta},
  address = {Edmonton, AB, Canada},
  year = {2009},
  url_pdf = {http://papersdb.cs.ualberta.ca/~papersdb/uploaded_files/1032/additional_thesis.pdf}
}