Theory

Needle In A Multimodal Haystack NeurIPS 2024 Neural Active Learning Beyond Bandits ICLR 2024 Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks NeurIPS 2024 Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space JMLR 2024 Neural Model Checking NeurIPS 2024 Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK JMLR 2024 Neural Oscillators for Generalization of Physics-Informed Machine Learning AAAI 2024 Neural Redshift: Random Networks are not Random Functions CVPR 2024 Neural Tangent Kernels for Axis-Aligned Tree Ensembles ICML 2024 New Lower Bounds for Testing Monotonicity and Log Concavity of Distributions COLT 2024 NN4SysBench: Characterizing Neural Network Verification for Computer Systems NeurIPS 2024 Noether's Razor: Learning Conserved Quantities NeurIPS 2024 Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning NeurIPS 2024 Non-convex Stochastic Composite Optimization with Polyak Momentum ICML 2024 Nonlinear dynamics of localization in neural receptive fields NeurIPS 2024 Nonlinear spiked covariance matrices and signal propagation in deep neural networks COLT 2024 Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery NeurIPS 2024 Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NeurIPS 2024 Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations ICLR 2024 Novelty vs. Potential Heuristics: A Comparison of Hardness Measures for Satisficing Planning AAAI 2024 NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics NeurIPS 2024 Now You See Me, Now You Don’t: ‘Poverty of the Stimulus’ Problems and Arbitrary Correspondences in End-to-End Speech Models COLING 2024 OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems ACL 2024 On Bias-Variance Alignment in Deep Models ICLR 2024 On Efficiently Representing Regular Languages as RNNs ACL 2024