Neural Networks

R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection ICLR 2025 RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes ICCV 2025 Random Feature Representation Boosting ICML 2025 Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising ICLR 2025 Random ReLU Neural Networks as Non-Gaussian Processes JMLR 2025 Range, not Independence, Drives Modularity in Biologically Inspired Representations ICLR 2025 RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone WACV 2025 RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians ICCV 2025 Real-Time Object Detection and Skeletonization for Motion Prediction in Video Streaming AAAI 2025 Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding CVPR 2025 Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation CVPR 2025 Reduced-rank Factorized Fourier Neural Operator ACML 2025 Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization ICCV 2025 RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects CVPR 2025 Regularized Neural Ensemblers AutoML 2025 Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks AISTATS 2025 Relational Object-Centric Actor-Critic CLeaR 2025 Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes ICCV 2025 Relaxed Rotational Equivariance via G-Biases in Vision AAAI 2025 ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing ICLR 2025 Representational Similarity via Interpretable Visual Concepts ICLR 2025 Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework AAAI 2025 ReSepNet: A Unified-Light Model for Recursive Speech Separation with Unknown Speaker Count Interspeech 2025 RESfM: Robust Deep Equivariant Structure from Motion ICLR 2025 ResFormer: All-Time Reservoir Memory for Long Sequence Classification EMNLP 2025