Deep Learning

On the Fourier analysis in the SO(3) space : the EquiLoPO Network ICLR 2025 On the Generalization of Representation Uncertainty in Earth Observation ICCV 2025 On the Geometry and Optimization of Polynomial Convolutional Networks AISTATS 2025 On the Guidance of Flow Matching ICML 2025 On the Hardness of Learning One Hidden Layer Neural Networks ALT 2025 On the Hardness of Training Deep Neural Networks Discretely AAAI 2025 On the Hölder Stability of Multiset and Graph Neural Networks ICLR 2025 On the Identifiability of Causal Abstractions AISTATS 2025 On the Importance of Embedding Norms in Self-Supervised Learning ICML 2025 On the Importance of Gaussianizing Representations ICML 2025 On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks ICML 2025 On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility IJCNLP 2025 On the Local Complexity of Linear Regions in Deep ReLU Networks ICML 2025 On the Optimal Memorization Capacity of Transformers ICLR 2025 On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent ICLR 2025 On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm JMLR 2025 On the Path to Make Ukrainian a High-Resource Language ACL 2025 On the Perception Bottleneck of VLMs for Chart Understanding EMNLP 2025 On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond AISTATS 2025 On the Power of Convolution-Augmented Transformer AAAI 2025 On the Power of Multitask Representation Learning with Gradient Descent AISTATS 2025 On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis UAI 2025 On the Provable Separation of Scales in Maximal Update Parameterization ICML 2025 On the Relationship between Accent Strength and Articulatory Features Interspeech 2025 On the Relationship Between Robustness and Expressivity of Graph Neural Networks AISTATS 2025