{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/relu","slug":"relu","name":"ReLU","full_name":null,"full_name_withheld":false,"description_markdown":null,"description_state":"withheld_vandalized","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Activation Functions","url":"/methods/category/activation-functions","pwc_aliases":[]}],"n_papers_tagged":10350,"archive_num_papers":10350,"papers_newest_first":[{"paper":null,"slug":"joint-angle-model-based-learning-to-refine","title":"Joint angle model based learning to refine kinematic human pose estimation","date":"2025-07-15","arxiv_id":"2507.11075","n_code_links":0,"syntology":null},{"paper":null,"slug":"admissibility-of-stein-shrinkage-for-batch","title":"Admissibility of Stein Shrinkage for Batch Normalization in the Presence of Adversarial Attacks","date":"2025-07-11","arxiv_id":"2507.08261","n_code_links":0,"syntology":null},{"paper":null,"slug":"softremish-a-novel-activation-function-for","title":"SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance","date":"2025-07-08","arxiv_id":"2507.06148","n_code_links":0,"syntology":null},{"paper":null,"slug":"determination-of-structural-cracks-using-deep","title":"Determination Of Structural Cracks Using Deep Learning Frameworks","date":"2025-07-03","arxiv_id":"2507.02416","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-objective-reinforcement-learning-for-6","title":"Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management","date":"2025-06-25","arxiv_id":"2506.20853","n_code_links":0,"syntology":null},{"paper":null,"slug":"stable-minima-of-relu-neural-networks-suffer","title":"Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon","date":"2025-06-25","arxiv_id":"2506.20779","n_code_links":0,"syntology":null},{"paper":null,"slug":"near-optimal-estimates-for-the-ell-p","title":"Near-optimal estimates for the $\\ell^p$-Lipschitz constants of deep random ReLU neural networks","date":"2025-06-24","arxiv_id":"2506.19695","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-algorithmic-construction-of-deep-relu","slug":"on-the-algorithmic-construction-of-deep-relu","title":"On the algorithmic construction of deep ReLU networks","date":"2025-06-23","arxiv_id":"2506.19104","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-guided-radiotherapy-treatment","title":"Physics-Guided Radiotherapy Treatment Planning with Deep Learning","date":"2025-06-23","arxiv_id":"2506.19880","n_code_links":0,"syntology":null},{"paper":null,"slug":"mtsic-multi-stage-transformer-based-gan-for","title":"MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization","date":"2025-06-21","arxiv_id":"2506.17540","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-mri-tumor-segmentation-using-hybrid","title":"Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention","date":"2025-06-18","arxiv_id":"2506.15562","n_code_links":0,"syntology":null},{"paper":"/paper/helena-high-efficiency-learning-based-channel","slug":"helena-high-efficiency-learning-based-channel","title":"HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention","date":"2025-06-16","arxiv_id":"2506.13408","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-prostate-gland-segmenting-using","title":"Improving Prostate Gland Segmenting Using Transformer based Architectures","date":"2025-06-16","arxiv_id":"2506.14844","n_code_links":0,"syntology":null},{"paper":null,"slug":"deploying-and-evaluating-multiple-deep","title":"Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection","date":"2025-06-14","arxiv_id":"2506.14834","n_code_links":0,"syntology":null},{"paper":null,"slug":"2506-10269","title":"Interior-Point Vanishing Problem in Semidefinite Relaxations for Neural Network Verification","date":"2025-06-12","arxiv_id":"2506.10269","n_code_links":0,"syntology":null},{"paper":null,"slug":"2506-10858","title":"Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation","date":"2025-06-12","arxiv_id":"2506.10858","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-digitization-of","title":"Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code","date":"2025-06-12","arxiv_id":"2506.10617","n_code_links":0,"syntology":null},{"paper":null,"slug":"mf2summ-multimodal-fusion-for-video","title":"MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment","date":"2025-06-12","arxiv_id":"2506.10430","n_code_links":0,"syntology":null},{"paper":null,"slug":"2506-10230","title":"Prompt-Guided Latent Diffusion with Predictive Class Conditioning for 3D Prostate MRI Generation","date":"2025-06-11","arxiv_id":"2506.10230","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-variational-contrastive","title":"Probabilistic Variational Contrastive Learning","date":"2025-06-11","arxiv_id":"2506.10159","n_code_links":0,"syntology":null},{"paper":"/paper/sampling-theory-for-super-resolution-with","slug":"sampling-theory-for-super-resolution-with","title":"Sampling Theory for Super-Resolution with Implicit Neural Representations","date":"2025-06-11","arxiv_id":"2506.09949","n_code_links":1,"syntology":null},{"paper":"/paper/2506-08357","slug":"2506-08357","title":"MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion","date":"2025-06-10","arxiv_id":"2506.08357","n_code_links":1,"syntology":null},{"paper":"/paper/2506-10031","slug":"2506-10031","title":"scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data","date":"2025-06-10","arxiv_id":"2506.10031","n_code_links":1,"syntology":null},{"paper":null,"slug":"2506-08205","title":"A Machine Learning Approach to Generate Residual Stress Distributions using Sparse Characterization Data in Friction-Stir Processed Parts","date":"2025-06-09","arxiv_id":"2506.08205","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-u-net-architectures","title":"A Comparative Study of U-Net Architectures for Change Detection in Satellite Images","date":"2025-06-09","arxiv_id":"2506.07925","n_code_links":0,"syntology":null},{"paper":"/paper/circumventing-backdoor-space-via-weight","slug":"circumventing-backdoor-space-via-weight","title":"Circumventing Backdoor Space via Weight Symmetry","date":"2025-06-09","arxiv_id":"2506.07467","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-models-aided-uplink-channel","title":"Diffusion Models-Aided Uplink Channel Estimation for RIS-Assisted Systems","date":"2025-06-09","arxiv_id":"2506.07770","n_code_links":0,"syntology":null},{"paper":null,"slug":"schauder-bases-for-c-0-1-using-relu-softplus","title":"Schauder Bases for $C[0, 1]$ Using ReLU, Softplus and Two Sigmoidal Functions","date":"2025-06-09","arxiv_id":"2506.07884","n_code_links":0,"syntology":null},{"paper":null,"slug":"spikesmoke-spiking-neural-networks-for","title":"SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding","date":"2025-06-09","arxiv_id":"2506.07737","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-breast-cancer-survival-disparities","title":"Analyzing Breast Cancer Survival Disparities by Race and Demographic Location: A Survival Analysis Approach","date":"2025-06-08","arxiv_id":"2506.07191","n_code_links":0,"syntology":null},{"paper":null,"slug":"magnet-a-multi-scale-attention-guided-graph","title":"MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection","date":"2025-06-08","arxiv_id":"2506.07126","n_code_links":0,"syntology":null},{"paper":null,"slug":"reliable-critics-monotonic-improvement-and","title":"Reliable Critics: Monotonic Improvement and Convergence Guarantees for Reinforcement Learning","date":"2025-06-08","arxiv_id":"2506.07134","n_code_links":0,"syntology":null},{"paper":"/paper/gradual-transition-from-bellman-optimality","slug":"gradual-transition-from-bellman-optimality","title":"Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning","date":"2025-06-06","arxiv_id":"2506.05968","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["motokiomura/annealed-q-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gs4-generalizable-sparse-splatting-semantic","title":"GS4: Generalizable Sparse Splatting Semantic SLAM","date":"2025-06-06","arxiv_id":"2506.06517","n_code_links":0,"syntology":null},{"paper":null,"slug":"regional-lattice-and-logical-representations","title":"Regional, Lattice and Logical Representations of Neural Networks","date":"2025-06-06","arxiv_id":"2506.05834","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-histological-synthesis-from-mass","title":"Deep histological synthesis from mass spectrometry imaging for multimodal registration","date":"2025-06-05","arxiv_id":"2506.05441","n_code_links":0,"syntology":null},{"paper":null,"slug":"partially-supervised-neural-network-model-for","title":"Partially-Supervised Neural Network Model For Quadratic Multiparametric Programming","date":"2025-06-05","arxiv_id":"2506.05567","n_code_links":0,"syntology":null},{"paper":null,"slug":"u-netmn-and-segnetmn-modified-u-net-and","title":"U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation","date":"2025-06-05","arxiv_id":"2506.05444","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-deep-reinforcement-learning-method","title":"A Novel Deep Reinforcement Learning Method for Computation Offloading in Multi-User Mobile Edge Computing with Decentralization","date":"2025-06-03","arxiv_id":"2506.02458","n_code_links":0,"syntology":null},{"paper":"/paper/simulate-any-radar-attribute-controllable","slug":"simulate-any-radar-attribute-controllable","title":"Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding","date":"2025-06-03","arxiv_id":"2506.03134","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhuxing0/sa-radar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dual-encoding-feature-filtering-generalized","slug":"dual-encoding-feature-filtering-generalized","title":"Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation","date":"2025-06-02","arxiv_id":"2506.02312","n_code_links":1,"syntology":null},{"paper":null,"slug":"exchangeability-in-neural-network","title":"Exchangeability in Neural Network Architectures and its Application to Dynamic Pruning","date":"2025-06-02","arxiv_id":"2506.02210","n_code_links":0,"syntology":null},{"paper":null,"slug":"trust-transformer-driven-u-net-for-sparse","title":"TRUST -- Transformer-Driven U-Net for Sparse Target Recovery","date":"2025-06-01","arxiv_id":"2506.01112","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-adversarial-attacks-on-cnn-based","title":"Black-box Adversarial Attacks on CNN-based SLAM Algorithms","date":"2025-05-30","arxiv_id":"2505.24654","n_code_links":0,"syntology":null},{"paper":"/paper/feature-attribution-from-first-principles","slug":"feature-attribution-from-first-principles","title":"Feature Attribution from First Principles","date":"2025-05-30","arxiv_id":"2505.24729","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-drift-estimation-for-ergodic","title":"Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration","date":"2025-05-30","arxiv_id":"2505.24383","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-networks-as-universal-finite-state-1","title":"Neural Networks as Universal Finite-State Machines: A Constructive ReLU Simulation Framework for NFAs","date":"2025-05-30","arxiv_id":"2505.24110","n_code_links":0,"syntology":null},{"paper":null,"slug":"qgan-based-data-augmentation-for-hybrid","title":"QGAN-based data augmentation for hybrid quantum-classical neural networks","date":"2025-05-30","arxiv_id":"2505.24780","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-failure-modes-of-deep-transformers-and","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","date":"2025-05-30","arxiv_id":"2505.24333","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-complexity-transform-adjustments-for","title":"Low-Complexity Transform Adjustments For Video Coding","date":"2025-05-29","arxiv_id":"2505.23618","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-rich-and-the-simple-on-the-implicit-bias","title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD","date":"2025-05-29","arxiv_id":"2505.24022","n_code_links":0,"syntology":null},{"paper":null,"slug":"binauralflow-a-causal-and-streamable-approach","title":"BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models","date":"2025-05-28","arxiv_id":"2505.22865","n_code_links":0,"syntology":null},{"paper":null,"slug":"calibrated-value-aware-model-learning-with","title":"Calibrated Value-Aware Model Learning with Stochastic Environment Models","date":"2025-05-28","arxiv_id":"2505.22772","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-bmd-estimation-from","title":"Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification","date":"2025-05-28","arxiv_id":"2505.22551","n_code_links":0,"syntology":null},{"paper":null,"slug":"fasttd3-simple-fast-and-capable-reinforcement","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","date":"2025-05-28","arxiv_id":"2505.22642","n_code_links":0,"syntology":null},{"paper":null,"slug":"multipath-cyclegan-for-harmonization-of","title":"Multipath cycleGAN for harmonization of paired and unpaired low-dose lung computed tomography reconstruction kernels","date":"2025-05-28","arxiv_id":"2505.22568","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithms-and-sq-lower-bounds-for-robustly","title":"Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-index Models","date":"2025-05-27","arxiv_id":"2505.21475","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-leaf-disease-classification-and","title":"Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism","date":"2025-05-27","arxiv_id":"2505.21316","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-incident-hypertension-prediction","title":"Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea","date":"2025-05-27","arxiv_id":"2505.20615","n_code_links":0,"syntology":null},{"paper":"/paper/laparoscopic-image-desmoking-using-the-u-net","slug":"laparoscopic-image-desmoking-using-the-u-net","title":"Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter","date":"2025-05-27","arxiv_id":"2505.21634","n_code_links":1,"syntology":null},{"paper":null,"slug":"supervised-and-self-supervised-land-cover","title":"Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands","date":"2025-05-27","arxiv_id":"2505.21269","n_code_links":0,"syntology":null},{"paper":null,"slug":"unpaired-image-to-image-translation-for","title":"Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing","date":"2025-05-27","arxiv_id":"2505.20746","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-spatial-aliasing","title":"Deep learning based spatial aliasing reduction in beamforming for audio capture","date":"2025-05-26","arxiv_id":"2505.19781","n_code_links":0,"syntology":null},{"paper":null,"slug":"improvement-strategies-for-few-shot-learning","title":"Improvement Strategies for Few-Shot Learning in OCT Image Classification of Rare Retinal Diseases","date":"2025-05-26","arxiv_id":"2505.20149","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-magnitude-preservation-and-rotation","title":"Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers","date":"2025-05-25","arxiv_id":"2505.19122","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-breast-cancer-detection","title":"Deep Learning for Breast Cancer Detection: Comparative Analysis of ConvNeXT and EfficientNet","date":"2025-05-24","arxiv_id":"2505.18725","n_code_links":0,"syntology":null},{"paper":null,"slug":"anatomy-guided-multitask-learning-for-mri","title":"Anatomy-Guided Multitask Learning for MRI-Based Classification of Placenta Accreta Spectrum and its Subtypes","date":"2025-05-23","arxiv_id":"2505.17484","n_code_links":0,"syntology":null},{"paper":"/paper/dual-attention-residual-u-net-for-accurate","slug":"dual-attention-residual-u-net-for-accurate","title":"Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection","date":"2025-05-23","arxiv_id":"2505.17683","n_code_links":1,"syntology":null},{"paper":null,"slug":"evm-fusion-an-explainable-vision-mamba","title":"EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion","date":"2025-05-23","arxiv_id":"2505.17367","n_code_links":0,"syntology":null},{"paper":"/paper/f-ancgan-an-attention-enhanced-cycle","slug":"f-ancgan-an-attention-enhanced-cycle","title":"F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles","date":"2025-05-23","arxiv_id":"2505.18106","n_code_links":1,"syntology":null},{"paper":"/paper/minkunext-si-improving-point-cloud-based","slug":"minkunext-si-improving-point-cloud-based","title":"MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity","date":"2025-05-23","arxiv_id":"2505.17591","n_code_links":1,"syntology":null},{"paper":null,"slug":"texttt-range-arithmetic-verifiable-deep","title":"\\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party","date":"2025-05-23","arxiv_id":"2505.17623","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-diffusion-models-don-t-memorize-the-role","title":"Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training","date":"2025-05-23","arxiv_id":"2505.17638","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-generalization-performance-of","title":"Assessing the generalization performance of SAM for ureteroscopy scene understanding","date":"2025-05-22","arxiv_id":"2505.17210","n_code_links":0,"syntology":null},{"paper":null,"slug":"critical-points-of-random-neural-networks","title":"Critical Points of Random Neural Networks","date":"2025-05-22","arxiv_id":"2505.17000","n_code_links":0,"syntology":null},{"paper":"/paper/deep-mineralogical-segmentation-of-thin","slug":"deep-mineralogical-segmentation-of-thin","title":"Deep mineralogical segmentation of thin section images based on QEMSCAN maps","date":"2025-05-22","arxiv_id":"2505.17008","n_code_links":1,"syntology":null},{"paper":null,"slug":"directional-convergence-benign-overfitting-of","title":"Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks","date":"2025-05-22","arxiv_id":"2505.16204","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-federated-survival-analysis-through","title":"Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare","date":"2025-05-22","arxiv_id":"2505.16190","n_code_links":0,"syntology":null},{"paper":null,"slug":"superpure-efficient-purification-of-localized","title":"SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models","date":"2025-05-22","arxiv_id":"2505.16318","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-computational-complexity-of-counting","title":"The Computational Complexity of Counting Linear Regions in ReLU Neural Networks","date":"2025-05-22","arxiv_id":"2505.16716","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-of-adam-in-deep-relu-networks-via","title":"Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds","date":"2025-05-21","arxiv_id":"2505.15013","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-explorer-a-plug-in-reinforcement-learning","title":"LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models","date":"2025-05-21","arxiv_id":"2505.15293","n_code_links":0,"syntology":null},{"paper":"/paper/one-layer-transformers-are-provably-optimal","slug":"one-layer-transformers-are-provably-optimal","title":"One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks","date":"2025-05-21","arxiv_id":"2505.15009","n_code_links":1,"syntology":null},{"paper":"/paper/rlbenchnet-the-right-network-for-the-right","slug":"rlbenchnet-the-right-network-for-the-right","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","date":"2025-05-21","arxiv_id":"2505.15040","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-reconstruction-from-sketches","title":"3D Reconstruction from Sketches","date":"2025-05-20","arxiv_id":"2505.14621","n_code_links":0,"syntology":null},{"paper":"/paper/aquasignal-an-integrated-framework-for-robust","slug":"aquasignal-an-integrated-framework-for-robust","title":"AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis","date":"2025-05-20","arxiv_id":"2505.14285","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-neural-network-expressivity","title":"Better Neural Network Expressivity: Subdividing the Simplex","date":"2025-05-20","arxiv_id":"2505.14338","n_code_links":0,"syntology":null},{"paper":"/paper/lod1-3d-city-model-from-lidar-the-impact-of","slug":"lod1-3d-city-model-from-lidar-the-impact-of","title":"LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction","date":"2025-05-20","arxiv_id":"2505.14747","n_code_links":1,"syntology":null},{"paper":"/paper/sample-and-computationally-efficient-1","slug":"sample-and-computationally-efficient-1","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","date":"2025-05-20","arxiv_id":"2505.14821","n_code_links":1,"syntology":null},{"paper":"/paper/ssps-self-supervised-positive-sampling-for","slug":"ssps-self-supervised-positive-sampling-for","title":"SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification","date":"2025-05-20","arxiv_id":"2505.14561","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-generating-realistic-underwater","title":"Towards Generating Realistic Underwater Images","date":"2025-05-20","arxiv_id":"2505.14296","n_code_links":0,"syntology":null},{"paper":"/paper/vulnerability-of-transfer-learned-neural","slug":"vulnerability-of-transfer-learned-neural","title":"Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime","date":"2025-05-20","arxiv_id":"2505.14323","n_code_links":1,"syntology":null},{"paper":"/paper/a-skull-adaptive-framework-for-ai-based-3d","slug":"a-skull-adaptive-framework-for-ai-based-3d","title":"A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation","date":"2025-05-19","arxiv_id":"2505.12998","n_code_links":1,"syntology":null},{"paper":null,"slug":"segmentation-of-temporomandibular-joint","title":"Segmentation of temporomandibular joint structures on mri images using neural networks for diagnosis of pathologies","date":"2025-05-19","arxiv_id":"2505.12963","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-enhanced-u-net-for-accurate","title":"Attention-Enhanced U-Net for Accurate Segmentation of COVID-19 Infected Lung Regions in CT Scans","date":"2025-05-18","arxiv_id":"2505.12298","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-low-field-to-high-value-robust-cortical","title":"From Low Field to High Value: Robust Cortical Mapping from Low-Field MRI","date":"2025-05-18","arxiv_id":"2505.12228","n_code_links":0,"syntology":null},{"paper":null,"slug":"road-segmentation-for-adas-ad-applications","title":"Road Segmentation for ADAS/AD Applications","date":"2025-05-18","arxiv_id":"2505.12206","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-10880","title":"Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions","date":"2025-05-16","arxiv_id":"2505.10880","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-11168","title":"CheX-DS: Improving Chest X-ray Image Classification with Ensemble Learning Based on DenseNet and Swin Transformer","date":"2025-05-16","arxiv_id":"2505.11168","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-classical-view-on-benign-overfitting-the","title":"A Classical View on Benign Overfitting: The Role of Sample Size","date":"2025-05-16","arxiv_id":"2505.11621","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":10350,"with_a_code_link":4256,"where_syntology_ran_a_sample":1079,"not_listed_spam_title":0,"listed":10350,"listed_where_code_ran":1079,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":901,"every_run_a_failure_of_syntologys_instrument":178,"listed_with_a_run_with_no_instrument_failure":901,"listed_every_run_a_failure_of_syntologys_instrument":178,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1079,"papers_where_code_ran_first_page":"/method/relu/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":104,"url":"/method/relu/papers/2","json":"/method/relu/papers/2.json","rows":100},{"order":"archive","page":3,"of":104,"url":"/method/relu/papers/3","json":"/method/relu/papers/3.json","rows":100},{"order":"archive","page":4,"of":104,"url":"/method/relu/papers/4","json":"/method/relu/papers/4.json","rows":100},{"order":"archive","page":5,"of":104,"url":"/method/relu/papers/5","json":"/method/relu/papers/5.json","rows":100},{"order":"archive","page":6,"of":104,"url":"/method/relu/papers/6","json":"/method/relu/papers/6.json","rows":100},{"order":"archive","page":7,"of":104,"url":"/method/relu/papers/7","json":"/method/relu/papers/7.json","rows":100},{"order":"archive","page":8,"of":104,"url":"/method/relu/papers/8","json":"/method/relu/papers/8.json","rows":100},{"order":"archive","page":9,"of":104,"url":"/method/relu/papers/9","json":"/method/relu/papers/9.json","rows":100},{"order":"archive","page":10,"of":104,"url":"/method/relu/papers/10","json":"/method/relu/papers/10.json","rows":100},{"order":"archive","page":11,"of":104,"url":"/method/relu/papers/11","json":"/method/relu/papers/11.json","rows":100},{"order":"archive","page":12,"of":104,"url":"/method/relu/papers/12","json":"/method/relu/papers/12.json","rows":100},{"order":"archive","page":13,"of":104,"url":"/method/relu/papers/13","json":"/method/relu/papers/13.json","rows":100},{"order":"archive","page":14,"of":104,"url":"/method/relu/papers/14","json":"/method/relu/papers/14.json","rows":100},{"order":"archive","page":15,"of":104,"url":"/method/relu/papers/15","json":"/method/relu/papers/15.json","rows":100},{"order":"archive","page":16,"of":104,"url":"/method/relu/papers/16","json":"/method/relu/papers/16.json","rows":100},{"order":"archive","page":17,"of":104,"url":"/method/relu/papers/17","json":"/method/relu/papers/17.json","rows":100},{"order":"archive","page":18,"of":104,"url":"/method/relu/papers/18","json":"/method/relu/papers/18.json","rows":100},{"order":"archive","page":19,"of":104,"url":"/method/relu/papers/19","json":"/method/relu/papers/19.json","rows":100},{"order":"archive","page":20,"of":104,"url":"/method/relu/papers/20","json":"/method/relu/papers/20.json","rows":100},{"order":"archive","page":21,"of":104,"url":"/method/relu/papers/21","json":"/method/relu/papers/21.json","rows":100},{"order":"archive","page":22,"of":104,"url":"/method/relu/papers/22","json":"/method/relu/papers/22.json","rows":100},{"order":"archive","page":23,"of":104,"url":"/method/relu/papers/23","json":"/method/relu/papers/23.json","rows":100},{"order":"archive","page":24,"of":104,"url":"/method/relu/papers/24","json":"/method/relu/papers/24.json","rows":100},{"order":"archive","page":25,"of":104,"url":"/method/relu/papers/25","json":"/method/relu/papers/25.json","rows":100},{"order":"archive","page":26,"of":104,"url":"/method/relu/papers/26","json":"/method/relu/papers/26.json","rows":100},{"order":"archive","page":27,"of":104,"url":"/method/relu/papers/27","json":"/method/relu/papers/27.json","rows":100},{"order":"archive","page":28,"of":104,"url":"/method/relu/papers/28","json":"/method/relu/papers/28.json","rows":100},{"order":"archive","page":29,"of":104,"url":"/method/relu/papers/29","json":"/method/relu/papers/29.json","rows":100},{"order":"archive","page":30,"of":104,"url":"/method/relu/papers/30","json":"/method/relu/papers/30.json","rows":100},{"order":"archive","page":31,"of":104,"url":"/method/relu/papers/31","json":"/method/relu/papers/31.json","rows":100},{"order":"archive","page":32,"of":104,"url":"/method/relu/papers/32","json":"/method/relu/papers/32.json","rows":100},{"order":"archive","page":33,"of":104,"url":"/method/relu/papers/33","json":"/method/relu/papers/33.json","rows":100},{"order":"archive","page":34,"of":104,"url":"/method/relu/papers/34","json":"/method/relu/papers/34.json","rows":100},{"order":"archive","page":35,"of":104,"url":"/method/relu/papers/35","json":"/method/relu/papers/35.json","rows":100},{"order":"archive","page":36,"of":104,"url":"/method/relu/papers/36","json":"/method/relu/papers/36.json","rows":100},{"order":"archive","page":37,"of":104,"url":"/method/relu/papers/37","json":"/method/relu/papers/37.json","rows":100},{"order":"archive","page":38,"of":104,"url":"/method/relu/papers/38","json":"/method/relu/papers/38.json","rows":100},{"order":"archive","page":39,"of":104,"url":"/method/relu/papers/39","json":"/method/relu/papers/39.json","rows":100},{"order":"archive","page":40,"of":104,"url":"/method/relu/papers/40","json":"/method/relu/papers/40.json","rows":100},{"order":"archive","page":41,"of":104,"url":"/method/relu/papers/41","json":"/method/relu/papers/41.json","rows":100},{"order":"archive","page":42,"of":104,"url":"/method/relu/papers/42","json":"/method/relu/papers/42.json","rows":100},{"order":"archive","page":43,"of":104,"url":"/method/relu/papers/43","json":"/method/relu/papers/43.json","rows":100},{"order":"archive","page":44,"of":104,"url":"/method/relu/papers/44","json":"/method/relu/papers/44.json","rows":100},{"order":"archive","page":45,"of":104,"url":"/method/relu/papers/45","json":"/method/relu/papers/45.json","rows":100},{"order":"archive","page":46,"of":104,"url":"/method/relu/papers/46","json":"/method/relu/papers/46.json","rows":100},{"order":"archive","page":47,"of":104,"url":"/method/relu/papers/47","json":"/method/relu/papers/47.json","rows":100},{"order":"archive","page":48,"of":104,"url":"/method/relu/papers/48","json":"/method/relu/papers/48.json","rows":100},{"order":"archive","page":49,"of":104,"url":"/method/relu/papers/49","json":"/method/relu/papers/49.json","rows":100},{"order":"archive","page":50,"of":104,"url":"/method/relu/papers/50","json":"/method/relu/papers/50.json","rows":100},{"order":"archive","page":51,"of":104,"url":"/method/relu/papers/51","json":"/method/relu/papers/51.json","rows":100},{"order":"archive","page":52,"of":104,"url":"/method/relu/papers/52","json":"/method/relu/papers/52.json","rows":100},{"order":"archive","page":53,"of":104,"url":"/method/relu/papers/53","json":"/method/relu/papers/53.json","rows":100},{"order":"archive","page":54,"of":104,"url":"/method/relu/papers/54","json":"/method/relu/papers/54.json","rows":100},{"order":"archive","page":55,"of":104,"url":"/method/relu/papers/55","json":"/method/relu/papers/55.json","rows":100},{"order":"archive","page":56,"of":104,"url":"/method/relu/papers/56","json":"/method/relu/papers/56.json","rows":100},{"order":"archive","page":57,"of":104,"url":"/method/relu/papers/57","json":"/method/relu/papers/57.json","rows":100},{"order":"archive","page":58,"of":104,"url":"/method/relu/papers/58","json":"/method/relu/papers/58.json","rows":100},{"order":"archive","page":59,"of":104,"url":"/method/relu/papers/59","json":"/method/relu/papers/59.json","rows":100},{"order":"archive","page":60,"of":104,"url":"/method/relu/papers/60","json":"/method/relu/papers/60.json","rows":100},{"order":"archive","page":61,"of":104,"url":"/method/relu/papers/61","json":"/method/relu/papers/61.json","rows":100},{"order":"archive","page":62,"of":104,"url":"/method/relu/papers/62","json":"/method/relu/papers/62.json","rows":100},{"order":"archive","page":63,"of":104,"url":"/method/relu/papers/63","json":"/method/relu/papers/63.json","rows":100},{"order":"archive","page":64,"of":104,"url":"/method/relu/papers/64","json":"/method/relu/papers/64.json","rows":100},{"order":"archive","page":65,"of":104,"url":"/method/relu/papers/65","json":"/method/relu/papers/65.json","rows":100},{"order":"archive","page":66,"of":104,"url":"/method/relu/papers/66","json":"/method/relu/papers/66.json","rows":100},{"order":"archive","page":67,"of":104,"url":"/method/relu/papers/67","json":"/method/relu/papers/67.json","rows":100},{"order":"archive","page":68,"of":104,"url":"/method/relu/papers/68","json":"/method/relu/papers/68.json","rows":100},{"order":"archive","page":69,"of":104,"url":"/method/relu/papers/69","json":"/method/relu/papers/69.json","rows":100},{"order":"archive","page":70,"of":104,"url":"/method/relu/papers/70","json":"/method/relu/papers/70.json","rows":100},{"order":"archive","page":71,"of":104,"url":"/method/relu/papers/71","json":"/method/relu/papers/71.json","rows":100},{"order":"archive","page":72,"of":104,"url":"/method/relu/papers/72","json":"/method/relu/papers/72.json","rows":100},{"order":"archive","page":73,"of":104,"url":"/method/relu/papers/73","json":"/method/relu/papers/73.json","rows":100},{"order":"archive","page":74,"of":104,"url":"/method/relu/papers/74","json":"/method/relu/papers/74.json","rows":100},{"order":"archive","page":75,"of":104,"url":"/method/relu/papers/75","json":"/method/relu/papers/75.json","rows":100},{"order":"archive","page":76,"of":104,"url":"/method/relu/papers/76","json":"/method/relu/papers/76.json","rows":100},{"order":"archive","page":77,"of":104,"url":"/method/relu/papers/77","json":"/method/relu/papers/77.json","rows":100},{"order":"archive","page":78,"of":104,"url":"/method/relu/papers/78","json":"/method/relu/papers/78.json","rows":100},{"order":"archive","page":79,"of":104,"url":"/method/relu/papers/79","json":"/method/relu/papers/79.json","rows":100},{"order":"archive","page":80,"of":104,"url":"/method/relu/papers/80","json":"/method/relu/papers/80.json","rows":100},{"order":"archive","page":81,"of":104,"url":"/method/relu/papers/81","json":"/method/relu/papers/81.json","rows":100},{"order":"archive","page":82,"of":104,"url":"/method/relu/papers/82","json":"/method/relu/papers/82.json","rows":100},{"order":"archive","page":83,"of":104,"url":"/method/relu/papers/83","json":"/method/relu/papers/83.json","rows":100},{"order":"archive","page":84,"of":104,"url":"/method/relu/papers/84","json":"/method/relu/papers/84.json","rows":100},{"order":"archive","page":85,"of":104,"url":"/method/relu/papers/85","json":"/method/relu/papers/85.json","rows":100},{"order":"archive","page":86,"of":104,"url":"/method/relu/papers/86","json":"/method/relu/papers/86.json","rows":100},{"order":"archive","page":87,"of":104,"url":"/method/relu/papers/87","json":"/method/relu/papers/87.json","rows":100},{"order":"archive","page":88,"of":104,"url":"/method/relu/papers/88","json":"/method/relu/papers/88.json","rows":100},{"order":"archive","page":89,"of":104,"url":"/method/relu/papers/89","json":"/method/relu/papers/89.json","rows":100},{"order":"archive","page":90,"of":104,"url":"/method/relu/papers/90","json":"/method/relu/papers/90.json","rows":100},{"order":"archive","page":91,"of":104,"url":"/method/relu/papers/91","json":"/method/relu/papers/91.json","rows":100},{"order":"archive","page":92,"of":104,"url":"/method/relu/papers/92","json":"/method/relu/papers/92.json","rows":100},{"order":"archive","page":93,"of":104,"url":"/method/relu/papers/93","json":"/method/relu/papers/93.json","rows":100},{"order":"archive","page":94,"of":104,"url":"/method/relu/papers/94","json":"/method/relu/papers/94.json","rows":100},{"order":"archive","page":95,"of":104,"url":"/method/relu/papers/95","json":"/method/relu/papers/95.json","rows":100},{"order":"archive","page":96,"of":104,"url":"/method/relu/papers/96","json":"/method/relu/papers/96.json","rows":100},{"order":"archive","page":97,"of":104,"url":"/method/relu/papers/97","json":"/method/relu/papers/97.json","rows":100},{"order":"archive","page":98,"of":104,"url":"/method/relu/papers/98","json":"/method/relu/papers/98.json","rows":100},{"order":"archive","page":99,"of":104,"url":"/method/relu/papers/99","json":"/method/relu/papers/99.json","rows":100},{"order":"archive","page":100,"of":104,"url":"/method/relu/papers/100","json":"/method/relu/papers/100.json","rows":100},{"order":"archive","page":101,"of":104,"url":"/method/relu/papers/101","json":"/method/relu/papers/101.json","rows":100},{"order":"archive","page":102,"of":104,"url":"/method/relu/papers/102","json":"/method/relu/papers/102.json","rows":100},{"order":"archive","page":103,"of":104,"url":"/method/relu/papers/103","json":"/method/relu/papers/103.json","rows":100},{"order":"archive","page":104,"of":104,"url":"/method/relu/papers/104","json":"/method/relu/papers/104.json","rows":50},{"order":"ran","page":1,"of":11,"url":"/method/relu/papers/ran/1","json":"/method/relu/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":11,"url":"/method/relu/papers/ran/2","json":"/method/relu/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":11,"url":"/method/relu/papers/ran/3","json":"/method/relu/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":11,"url":"/method/relu/papers/ran/4","json":"/method/relu/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":11,"url":"/method/relu/papers/ran/5","json":"/method/relu/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":11,"url":"/method/relu/papers/ran/6","json":"/method/relu/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":11,"url":"/method/relu/papers/ran/7","json":"/method/relu/papers/ran/7.json","rows":100},{"order":"ran","page":8,"of":11,"url":"/method/relu/papers/ran/8","json":"/method/relu/papers/ran/8.json","rows":100},{"order":"ran","page":9,"of":11,"url":"/method/relu/papers/ran/9","json":"/method/relu/papers/ran/9.json","rows":100},{"order":"ran","page":10,"of":11,"url":"/method/relu/papers/ran/10","json":"/method/relu/papers/ran/10.json","rows":100},{"order":"ran","page":11,"of":11,"url":"/method/relu/papers/ran/11","json":"/method/relu/papers/ran/11.json","rows":79}],"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":1162},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1128},{"task":"/task/image-classification","name":"Image Classification","papers":735},{"task":"/task/image-classification","name":"image-classification","papers":570},{"task":"/task/decoder","name":"Decoder","papers":558},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":543},{"task":"/task/translation","name":"Translation","papers":542},{"task":"/task/object-detection","name":"Object Detection","papers":504},{"task":"/task/classification","name":"General Classification","papers":493},{"task":"/task/object-detection-1","name":"object-detection","papers":444},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":404},{"task":"/task/deep-learning","name":"Deep Learning","papers":374},{"task":"/task/classification-1","name":"Classification","papers":369},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":364},{"task":"/task/machine-translation","name":"Machine Translation","papers":320},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":313},{"task":"/task/image-generation","name":"Image Generation","papers":300},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":291},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":281},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":273}],"tasks_shown":20,"n_tasks":1701,"usage_by_year":[{"year":"2012","papers":1},{"year":"2013","papers":3},{"year":"2014","papers":10},{"year":"2015","papers":61},{"year":"2016","papers":136},{"year":"2017","papers":355},{"year":"2018","papers":842},{"year":"2019","papers":1610},{"year":"2020","papers":1972},{"year":"2021","papers":1362},{"year":"2022","papers":1136},{"year":"2023","papers":1166},{"year":"2024","papers":1164},{"year":"2025","papers":532}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/relu"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=ReLU","read_at":"2026-10-05T01:01:05+00:00","query":"ReLU","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'ReLU' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["P-ReLU","ReLU code space","log-sum-ReLU (LSR)","Brownian ReLU (Br-ReLU)","Height-Augmented ReLU Networks","Pixel-wise Dynamic ReLU (P-DyReLU)","Sparse-Activation-ReLU (SAR) layer","ReLU-Catalyzed Abstraction Refinement"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"afbd1497a5c538a9a341bf3d09b5854039642e4ca4f1fc71196db67013600c96","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}