Robuta

https://openreview.net/forum?id=tfGuvCp50e Expressivity of Shallow Neural Networks Over Finite Fields | OpenReview We study the expressivity of shallow polynomial neural networks (PNNs) with monomial activation functions over finite fields. For a given architecture, we... neural networksfinite fieldsexpressivityshallowopenreview https://openreview.net/forum?id=rdv6yeMFpn&referrer=%5Bthe%20profile%20of%20Haggai%20Maron%5D(%2Fprofile%3Fid%3D~Haggai_Maron1) Homomorphism Expressivity of Spectral Invariant Graph Neural Networks | OpenReview Graph spectra are an important class of structural features on graphs that have shown promising results in enhancing Graph Neural Networks (GNNs). Despite... graph neural networkshomomorphismexpressivityspectralinvariant https://openreview.net/forum?id=ytwpZDDOkb Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification |... Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform... enhancingexpressivitytemporal https://huggingface.co/papers/2305.02582 Paper page - On the Expressivity Role of LayerNorm in Transformers' Attention Join the discussion on this paper page on thepaperexpressivity https://arxiv.org/abs/2111.00876 [2111.00876] On the Expressivity of Markov Reward Abstract page for arXiv paper 2111.00876: On the Expressivity of Markov Reward on the211100876expressivitymarkov https://github.com/facebookresearch/shaDow_GNN GitHub - facebookresearch/shaDow_GNN: [NeurIPS 2021]: Improve the GNN expressivity and scalability... [NeurIPS 2021]: Improve the GNN expressivity and scalability by decoupling the depth and receptive field of state-of-the-art GNN architectures -... neurips 2021githubshadowgnn https://arxiv.org/abs/1205.0627 [1205.0627] Rule-weighted and terminal-weighted context-free grammars have identical expressivity Abstract page for arXiv paper 1205.0627: Rule-weighted and terminal-weighted context-free grammars have identical expressivity context free grammars https://openreview.net/forum?id=hbtG6s6e7r Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally | OpenReview Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In... growingtinynetworksspottingexpressivity https://openreview.net/forum?id=awHTL3Hpto Expressivity of ReLU-Networks under Convex Relaxations | OpenReview Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly... expressivityrelunetworksconvexrelaxations https://openreview.net/forum?id=Qms9kWnbpP Expressivity of Spiking Neural Networks through the Spike Response Model | OpenReview This article studies the expressive power of spiking neural networks with firing-time-based information encoding, highlighting their potential for future... spiking neural networksspike response modelthrough theexpressivity https://arxiv.org/abs/2505.14338 [2505.14338] Better Neural Network Expressivity: Subdividing the Simplex Abstract page for arXiv paper 2505.14338: Better Neural Network Expressivity: Subdividing the Simplex neural network2505betterexpressivitysubdividing https://openreview.net/forum?id=enWAn9QtYz&referrer=%5Bthe%20profile%20of%20Nils%20Morten%20Kriege%5D(%2Fprofile%3Fid%3D~Nils_Morten_Kriege1) On the Relationship Between Robustness and Expressivity of Graph Neural Networks | OpenReview We investigate the vulnerability of Graph Neural Networks (GNNs) to bit-flip attacks (BFAs) by introducing an analytical framework to study the influence of... graph neural networkson the https://openreview.net/forum?id=9DlCh34E1bN On the Expressivity of Markov Reward | OpenReview We study the expressivity of Markov reward functions in finite environments by inspecting what kinds of tasks such functions can express. on theexpressivitymarkovrewardopenreview https://openreview.net/forum?id=0IJQD8zRXT Positional Attention: Expressivity and Learnability of Algorithmic Computation | OpenReview There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of... positionalattentionexpressivitylearnabilityalgorithmic https://arxiv.org/abs/2505.23635 [2505.23635] Expressivity of bisimulation pseudometrics over analytic state spaces Abstract page for arXiv paper 2505.23635: Expressivity of bisimulation pseudometrics over analytic state spaces 2505expressivitybisimulationanalyticstate https://pmc.ncbi.nlm.nih.gov/articles/PMC12603653/ A sensorimotor basis for facial expressivity differences in autism - PMC In autism, differences in the appearance, timing, and intensity of facial expressions are a major barrier to social communication. While disrupted sensorimotor... sensorimotorbasisfacialexpressivitydifferences https://www.kth.se/sv/philhist/historia/forskning/tidigare-forskningsprojekt/cosmopolitanism-from-the-margins-mediations-of-expressivity-social-space-and-cultural-citizenship-1.504465 Cosmopolitanism from the Margins: Mediations of Expressivity, Social Space and Cultural Citizenship... from the