Neural Networks

Unboxed: Geometrically and Temporally Consistent Video Outpainting CVPR 2025 Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling EMNLP 2025 Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing ICLR 2025 Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity ICML 2025 Understanding Mode Connectivity via Parameter Space Symmetry ICML 2025 Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025 Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More ICML 2025 U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models ICLR 2025 UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale ICCV 2025 UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation ICML 2025 Universality of Real Minimal Complexity Reservoir AAAI 2025 Universal Neural Optimal Transport ICML 2025 Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment ICML 2025 Universal Speech Enhancement with Regression and Generative Mamba Interspeech 2025 Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition AAAI 2025 Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues ICLR 2025 Unlocking the Power of LSTM for Long Term Time Series Forecasting AAAI 2025 Validating Mechanistic Interpretations: An Axiomatic Approach ICML 2025 VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting ICCV 2025 Verification of Neural Networks Against Convolutional Perturbations via Parameterised Kernels AAAI 2025 VI^3NR: Variance Informed Initialization for Implicit Neural Representations CVPR 2025 Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation CVPR 2025 Video Individual Counting for Moving Drones ICCV 2025 VidSole: A Multimodal Dataset for Joint Kinetics Quantification and Disease Detection with Deep Learning AAAI 2025 ViLU: Learning Vision-Language Uncertainties for Failure Prediction ICCV 2025