World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. In this work, we propose a JEPA-style world model in which, rather than learning arbitrary latent dynamics, we restrict them to follow a bilinear parameterization.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Alejandro Ribeiro
[2601.17274] Unrolled Neural Networks for Constrained Optimization
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2408.15094] Constrained Diffusion Models via Dual Training
The Accessibility Forum starts next week! Sign up and join us in September.
[2408.13878] Generalization of Graph Neural Networks is Robust to Model Mismatch
The Accessibility Forum starts next week! Sign up and join us in September.
Computer Science > Machine Learning
[Submitted on 11 Jan 2024 (v1), last revised 12 Mar 2026 (this version, v3)] View PDF Subjects: Machine Learning (cs.LG); Signal Processing (eess.SP) Cite as: arXiv:2401.06279 [cs.LG] (or arXiv:2401.06279v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2401.06279
[2306.11700] Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
[Submitted on 20 Jun 2023 ( v1 ), last revised 17 Jan 2024 (this version, v2)] Title:Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs Download a PDF of the paper titled Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs, by Dongsheng Ding and Chen-Yu Wei and Kaiqing Zhang and Alejandro Ribeiro Download PDF HTML (experimental) Abstract:We study the problem of computing an optimal policy of an infinite-horizon discounted constrained...
Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs
[Submitted on 29 May 2023 ( v1 ), last revised 28 Jun 2023 (this version, v2)] Title:Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs Download a PDF of the paper titled Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs, by Zhiyang Wang and Luana Ruiz and Alejandro Ribeiro Download PDF Abstract: This paper studies the relationship between a graph neural network (GNN) and a manifold neural network (MNN)...
[2212.08171] Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis
[Submitted on 19 May 2022 ( v1 ), last revised 21 Jul 2023 (this version, v3)] Title:Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis Download a PDF of the paper titled Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis, by Charilaos I.
[2112.04629] Transferability Properties of Graph Neural Networks
[Submitted on 9 Dec 2021 ( v1 ), last revised 7 Aug 2023 (this version, v4)] Title:Transferability Properties of Graph Neural Networks Download a PDF of the paper titled Transferability Properties of Graph Neural Networks, by Luana Ruiz and 2 other authors Download PDF Abstract: Graph neural networks (GNNs) are composed of layers consisting of graph convolutions and pointwise nonlinearities.
[2108.09923] Convolutional Filtering and Neural Networks with Non Commutative Algebras
[Submitted on 23 Aug 2021 ( v1 ), last revised 6 Jul 2023 (this version, v3)] Title:Convolutional Filtering and Neural Networks with Non Commutative Algebras Download a PDF of the paper titled Convolutional Filtering and Neural Networks with Non Commutative Algebras, by Alejandro Parada-Mayorga and 1 other authors Download PDF Abstract: In this paper we introduce and study the algebraic generalization of non commutative convolutional neural networks.
[2106.03725] Stability to Deformations of Manifold Filters and Manifold Neural Networks
[Submitted on 7 Jun 2021 ( v1 ), last revised 14 Mar 2024 (this version, v5)] Title:Stability to Deformations of Manifold Filters and Manifold Neural Networks Download a PDF of the paper titled Stability to Deformations of Manifold Filters and Manifold Neural Networks, by Zhiyang Wang and 2 other authors Download PDF Abstract:The paper defines and studies manifold (M) convolutional filters and neural networks (NNs).
State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards
[Submitted on 23 Feb 2021 ( v1 ), last revised 21 Sep 2023 (this version, v2)] Title:State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards Download a PDF of the paper titled State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards, by Miguel Calvo-Fullana and 3 other authors Download PDF Abstract:A common formulation of constrained reinforcement learning involves multiple rewards that must...
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Alejandro
Contact Alejandro, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack