Siamak Ravanbakhsh

92 papers A* 24A 5Journal 56Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Inverting Data Transformations via Diffusion Sampling. CoRR Jinwoo Kim, Sékou-Oumar Kaba, Jiyun Park, Seunghoon Hong, Siamak Ravanbakhsh
2026	J	`jnl`	The Expressive Limits of Diagonal SSMs for State-Tracking. CoRR Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh, Sarath Chandar
2025	J	`jnl`	Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs. CoRR Mehran Shakerinava, Siamak Ravanbakhsh, Adam Oberman
2025	J	`jnl`	Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models. CoRR Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh
2025	J	`jnl`	Energy Loss Functions for Physical Systems. CoRR Sékou-Oumar Kaba, Kusha Sareen, Daniel Levy, Siamak Ravanbakhsh
2025	J	`jnl`	Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism. CoRR Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
2025	J	`jnl`	Multi-Armed Sampling Problem and the End of Exploration. CoRR Mohammad Pedramfar, Siamak Ravanbakhsh
2025	A	`conf`	On the Identifiability of Causal Abstractions. AISTATS Xiusi Li, Sékou-Oumar Kaba, Siamak Ravanbakhsh
2025	J	`jnl`	On the Identifiability of Causal Abstractions. CoRR Xiusi Li, Sékou-Oumar Kaba, Siamak Ravanbakhsh
2025	J	`jnl`	Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMs. CoRR Behnoush Khavari, Mehran Shakerinava, Jayesh Khullar, Jerry Huang, François Rivest, Siamak Ravanbakhsh, Sarath Chandar
2025	J	`jnl`	Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities. CoRR Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein, Dominique Beaini, Siamak Ravanbakhsh, Kirill Neklyudov, Alexander Tong
2025	J	`jnl`	Scaling Laws and Symmetry, Evidence from Neural Force Fields. CoRR Nhat Khang Ngo, Siamak Ravanbakhsh
2025	A*	`conf`	SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models. ICLR Daniel Levy, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Qiang Zhu, Kin Long Kelvin Lee, Mikhail Galkin, Santiago Miret, Siamak Ravanbakhsh
2025	J	`jnl`	SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models. CoRR Daniel Levy, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Qiang Zhu, Kin Long Kelvin Lee, Mikhail Galkin, Santiago Miret, Siamak Ravanbakhsh
2025	J	`jnl`	Symmetry-Aware Generative Modeling through Learned Canonicalization. CoRR Kusha Sareen, Daniel Levy, Arnab Kumar Mondal, Sékou-Oumar Kaba, Tara Akhound-Sadegh, Siamak Ravanbakhsh
2024	A	`conf`	E(3)-Equivariant Mesh Neural Networks. AISTATS Thuan Anh Trang, Nhat Khang Ngo, Daniel Levy, Ngoc Thieu Vo, Siamak Ravanbakhsh, Truong Son Hy
2024	J	`jnl`	E(3)-Equivariant Mesh Neural Networks. CoRR Thuan N. A. Trang, Nhat Khang Ngo, Daniel Levy, Thieu N. Vo, Siamak Ravanbakhsh, Truong Son Hy
2024	A*	`conf`	Efficient Dynamics Modeling in Interactive Environments with Koopman Theory. ICLR Arnab Kumar Mondal, Siba Smarak Panigrahi, Sai Rajeswar, Kaleem Siddiqi, Siamak Ravanbakhsh
2024	A*	`conf`	Iterated Denoising Energy Matching for Sampling from Boltzmann Densities. ICML Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
2024	J	`jnl`	Iterated Denoising Energy Matching for Sampling from Boltzmann Densities. CoRR Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
2024	A*	`conf`	Learning to Reach Goals via Diffusion. ICML Vineet Jain, Siamak Ravanbakhsh
2024	A*	`conf`	On Diffusion Modeling for Anomaly Detection. ICLR Victor Livernoche, Vineet Jain, Yashar Hezaveh, Siamak Ravanbakhsh
2024	J	`jnl`	Sampling from Energy-based Policies using Diffusion. CoRR Vineet Jain, Tara Akhound-Sadegh, Siamak Ravanbakhsh
2024	J	`jnl`	Scalable Hierarchical Self-Attention with Learnable Hierarchy for Long-Range Interactions. Trans. Mach. Learn. Res. Thuan Nguyen Anh Trang, Nhat Khang Ngo, Hugo Sonnery, Thieu N. Vo, Siamak Ravanbakhsh, Truong Son Hy
2024	A	`conf`	Weight-Sharing Regularization. AISTATS Mehran Shakerinava, Motahareh Sohrabi, Siamak Ravanbakhsh, Simon Lacoste-Julien
2023	J	`jnl`	Efficient Dynamics Modeling in Interactive Environments with Koopman Theory. CoRR Arnab Kumar Mondal, Siba Smarak Panigrahi, Sai Rajeswar, Kaleem Siddiqi, Siamak Ravanbakhsh
2023	A*	`conf`	Equivariance with Learned Canonicalization Functions. ICML Sékou-Oumar Kaba, Arnab Kumar Mondal, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
2023	A*	`conf`	Equivariant Adaptation of Large Pretrained Models. NeurIPS Arnab Kumar Mondal, Siba Smarak Panigrahi, Oumar Kaba, Sai Mudumba, Siamak Ravanbakhsh
2023	J	`jnl`	Equivariant Adaptation of Large Pretrained Models. CoRR Arnab Kumar Mondal, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Sai Rajeswar, Siamak Ravanbakhsh
2023	J	`jnl`	Learning to Reach Goals via Diffusion. CoRR Vineet Jain, Siamak Ravanbakhsh
2023	J	`jnl`	Lie Point Symmetry and Physics Informed Networks. CoRR Tara Akhound-Sadegh, Laurence Perreault Levasseur, Johannes Brandstetter, Max Welling, Siamak Ravanbakhsh
2023	A*	`conf`	Lie Point Symmetry and Physics-Informed Networks. NeurIPS Tara Akhound-Sadegh, Laurence Perreault Levasseur, Johannes Brandstetter, Max Welling, Siamak Ravanbakhsh
2023	J	`jnl`	On Diffusion Modeling for Anomaly Detection. CoRR Victor Livernoche, Vineet Jain, Yashar Hezaveh, Siamak Ravanbakhsh
2023	J	`jnl`	Symmetry Breaking and Equivariant Neural Networks. CoRR Sékou-Oumar Kaba, Siamak Ravanbakhsh
2023	J	`jnl`	Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks. CoRR Daniel Levy, Sékou-Oumar Kaba, Carmelo Gonzales, Santiago Miret, Siamak Ravanbakhsh
2023	J	`jnl`	Weight-Sharing Regularization. CoRR Mehran Shakerinava, Motahareh Sohrabi, Siamak Ravanbakhsh, Simon Lacoste-Julien
2022	A*	`conf`	EqR: Equivariant Representations for Data-Efficient Reinforcement Learning. ICML Arnab Kumar Mondal, Vineet Jain, Kaleem Siddiqi, Siamak Ravanbakhsh
2022	J	`jnl`	Equivariance with Learned Canonicalization Functions. CoRR Sékou-Oumar Kaba, Arnab Kumar Mondal, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
2022	A*	`conf`	Equivariant Networks for Crystal Structures. NeurIPS Sékou-Oumar Kaba, Siamak Ravanbakhsh
2022	J	`jnl`	Equivariant Networks for Crystal Structures. CoRR Sékou-Oumar Kaba, Siamak Ravanbakhsh
2022	J	`jnl`	SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks. CoRR Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh
2022	A*	`conf`	SpeqNets: Sparsity-aware permutation-equivariant graph networks. ICML Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh
2022	A*	`conf`	Structuring Representations Using Group Invariants. NeurIPS Mehran Shakerinava, Arnab Kumar Mondal, Siamak Ravanbakhsh
2022	J	`jnl`	Transformation Coding: Simple Objectives for Equivariant Representations. CoRR Mehran Shakerinava, Arnab Kumar Mondal, Siamak Ravanbakhsh
2022	A*	`conf`	Utility Theory for Sequential Decision Making. ICML Mehran Shakerinava, Siamak Ravanbakhsh
2022	J	`jnl`	Utility Theory for Sequential Decision Making. CoRR Mehran Shakerinava, Siamak Ravanbakhsh
2021	A*	`conf`	Equivariant Networks for Pixelized Spheres. ICML Mehran Shakerinava, Siamak Ravanbakhsh
2021	J	`jnl`	Equivariant Networks for Pixelized Spheres. CoRR Mehran Shakerinava, Siamak Ravanbakhsh
2020	J	`jnl`	Equivariant Maps for Hierarchical Structures. CoRR Renhao Wang, Marjan Albooyeh, Siamak Ravanbakhsh
2020	A*	`conf`	Equivariant Networks for Hierarchical Structures. NeurIPS Renhao Wang, Marjan Albooyeh, Siamak Ravanbakhsh
2020	A*	`conf`	Universal Equivariant Multilayer Perceptrons. ICML Siamak Ravanbakhsh
2020	J	`jnl`	Universal Equivariant Multilayer Perceptrons. CoRR Siamak Ravanbakhsh
2019	J	`jnl`	Deep Models for Relational Databases. CoRR Devon R. Graham, Siamak Ravanbakhsh
2019	A*	`conf`	Improved Knowledge Graph Embedding Using Background Taxonomic Information. AAAI Bahare Fatemi, Siamak Ravanbakhsh, David Poole
2019	J	`jnl`	Incidence Networks for Geometric Deep Learning. CoRR Marjan Albooyeh, Daniele Bertolini, Siamak Ravanbakhsh
2019	J	`jnl`	Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines. Neural Process. Lett. Jakub M. Tomczak, Szymon Zareba, Siamak Ravanbakhsh, Russell Greiner
2018	—	`conf`	Analysis of Cosmic Microwave Background with Deep Learning. ICLR (Workshop) Siyu He, Siamak Ravanbakhsh, Shirley Ho
2018	A*	`conf`	Deep Models of Interactions Across Sets. ICML Jason S. Hartford, Devon R. Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh
2018	J	`jnl`	Deep Models of Interactions Across Sets. CoRR Jason S. Hartford, Devon R. Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh
2018	J	`jnl`	Improved Knowledge Graph Embedding using Background Taxonomic Information. CoRR Bahare Fatemi, Siamak Ravanbakhsh, David Poole
2018	J	`jnl`	Learning to Predict the Cosmological Structure Formation. CoRR Siyu He, Yin Li, Yu Feng, Shirley Ho, Siamak Ravanbakhsh, Wei Chen, Barnabás Póczos
2018	—	`conf`	Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector. MICCAI (1) Sumedha Singla, Mingming Gong, Siamak Ravanbakhsh, Frank C. Sciurba, Barnabás Póczos, Kayhan N. Batmanghelich
2018	J	`jnl`	Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector. CoRR Sumedha Singla, Mingming Gong, Siamak Ravanbakhsh, Frank C. Sciurba, Barnabás Póczos, Kayhan N. Batmanghelich
2017	—	`conf`	Deep Learning with Sets and Point Clouds. ICLR (Workshop) Siamak Ravanbakhsh, Jeff G. Schneider, Barnabás Póczos
2017	—	`conf`	Deep Sets. NIPS Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabás Póczos, Ruslan Salakhutdinov, Alexander J. Smola
2017	J	`jnl`	Deep Sets. CoRR Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabás Póczos, Ruslan Salakhutdinov, Alexander J. Smola
2017	A*	`conf`	Enabling Dark Energy Science with Deep Generative Models of Galaxy Images. AAAI Siamak Ravanbakhsh, François Lanusse, Rachel Mandelbaum, Jeff G. Schneider, Barnabás Póczos
2017	A*	`conf`	Equivariance Through Parameter-Sharing. ICML Siamak Ravanbakhsh, Jeff G. Schneider, Barnabás Póczos
2017	J	`jnl`	Equivariance Through Parameter-Sharing. CoRR Siamak Ravanbakhsh, Jeff G. Schneider, Barnabás Póczos
2017	J	`jnl`	Estimating Cosmological Parameters from the Dark Matter Distribution. CoRR Siamak Ravanbakhsh, Junier B. Oliva, Sebastian Fromenteau, Layne C. Price, Shirley Ho, Jeff G. Schneider, Barnabás Póczos
2017	—	`conf`	Min-Max Propagation. NIPS Christopher Srinivasa, Inmar E. Givoni, Siamak Ravanbakhsh, Brendan J. Frey
2016	J	`jnl`	Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM. CoRR Chun-Liang Li, Siamak Ravanbakhsh, Barnabás Póczos
2016	A*	`conf`	Boolean Matrix Factorization and Noisy Completion via Message Passing. ICML Siamak Ravanbakhsh, Barnabás Póczos, Russell Greiner
2016	J	`jnl`	Deep Learning with Sets and Point Clouds. CoRR Siamak Ravanbakhsh, Jeff G. Schneider, Barnabás Póczos
2016	J	`jnl`	Enabling Dark Energy Science with Deep Generative Models of Galaxy Images. CoRR Siamak Ravanbakhsh, François Lanusse, Rachel Mandelbaum, Jeff G. Schneider, Barnabás Póczos
2016	A*	`conf`	Estimating Cosmological Parameters from the Dark Matter Distribution. ICML Siamak Ravanbakhsh, Junier B. Oliva, Sebastian Fromenteau, Layne Price, Shirley Ho, Jeff G. Schneider, Barnabás Póczos
2016	A	`conf`	Stochastic Neural Networks with Monotonic Activation Functions. AISTATS Siamak Ravanbakhsh, Barnabás Póczos, Jeff G. Schneider, Dale Schuurmans, Russell Greiner
2016	J	`jnl`	Stochastic Neural Networks with Monotonic Activation Functions. CoRR Siamak Ravanbakhsh, Barnabás Póczos, Jeff G. Schneider, Dale Schuurmans, Russell Greiner
2016	A	`conf`	Survey Propagation beyond Constraint Satisfaction Problems. AISTATS Christopher Srinivasa, Siamak Ravanbakhsh, Brendan J. Frey
2015	J	`jnl`	Boolean Matrix Factorization and Completion via Message Passing. CoRR Siamak Ravanbakhsh, Russell Greiner
2015	—	`conf`	Embedding Inference for Structured Multilabel Prediction. NIPS Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Nan Ding, Dale Schuurmans
2015	J	`jnl`	Message Passing and Combinatorial Optimization. CoRR Siamak Ravanbakhsh
2015	J	`jnl`	Perturbed message passing for constraint satisfaction problems. J. Mach. Learn. Res. Siamak Ravanbakhsh, Russell Greiner
2014	J	`jnl`	Accurate, fully-automated NMR spectral profiling for metabolomics. CoRR Siamak Ravanbakhsh, Philip Liu, Trent C. Bjorndahl, Rupasri Mandal, Jason R. Grant, Michael Wilson, Roman Eisner, Igor Sinelnikov, Xiaoyu Hu, Claudio Luchinat, Russell Greiner, David S. Wishart
2014	J	`jnl`	Algebra of inference in graphical models revisited. CoRR Siamak Ravanbakhsh, Russell Greiner
2014	—	`conf`	Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning. NIPS Siamak Ravanbakhsh, Reihaneh Rabbany, Russell Greiner
2014	J	`jnl`	Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning. CoRR Siamak Ravanbakhsh, Reihaneh Rabbany, Russell Greiner
2014	A*	`conf`	Min-Max Problems on Factor Graphs. ICML Siamak Ravanbakhsh, Christopher Srinivasa, Brendan J. Frey, Russell Greiner
2014	J	`jnl`	Perturbed Message Passing for Constraint Satisfaction Problems. CoRR Siamak Ravanbakhsh, Russell Greiner
2014	J	`jnl`	Training Restricted Boltzmann Machine by Perturbation. CoRR Siamak Ravanbakhsh, Russell Greiner, Brendan J. Frey
2012	J	`jnl`	A Generalized Loop Correction Method for Approximate Inference in Graphical Models CoRR Siamak Ravanbakhsh, Chun-Nam Yu, Russell Greiner
2012	A*	`conf`	A Generalized Loop Correction Method for Approximate Inference in Graphical Models. ICML Siamak Ravanbakhsh, Chun-Nam Yu, Russell Greiner