[ { "id": 47, "size": 19256, "top_tags": [ { "tag": "deep learning", "n": 1903 }, { "tag": "CNN", "n": 1771 }, { "tag": "convolutional neural networks", "n": 1570 }, { "tag": "object detection", "n": 1426 }, { "tag": "computer vision", "n": 1129 }, { "tag": "semantic segmentation", "n": 1128 }, { "tag": "deep neural networks", "n": 886 }, { "tag": "convolutional neural network", "n": 736 } ], "top_papers": [ { "paper_id": "arxiv:1409.1556", "title": "Very Deep Convolutional Networks for Large-Scale Image Recognition", "citation_count": 75505, "source": "arxiv" }, { "paper_id": "arxiv:2010.11929", "title": "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale", "citation_count": 21539, "source": "arxiv" }, { "paper_id": "arxiv:1503.03832", "title": "FaceNet: A unified embedding for face recognition and clustering", "citation_count": 11116, "source": "arxiv" }, { "paper_id": "arxiv:2004.10934", "title": "YOLOv4: Optimal Speed and Accuracy of Object Detection", "citation_count": 10427, "source": "arxiv" }, { "paper_id": "arxiv:1706.05587", "title": "Rethinking Atrous Convolution for Semantic Image Segmentation", "citation_count": 7447, "source": "arxiv" } ] }, { "id": 15, "size": 14503, "top_tags": [ { "tag": "np -", "n": 834 }, { "tag": "NP", "n": 799 }, { "tag": "planar graphs", "n": 592 }, { "tag": "graph g", "n": 562 }, { "tag": "maximum degree", "n": 525 }, { "tag": "minimum number", "n": 512 }, { "tag": "n$ vertices", "n": 491 }, { "tag": "polynomial time", "n": 486 } ], "top_papers": [ { "paper_id": "arxiv:2105.10386", "title": "Analysis of Boolean Functions", "citation_count": 731, "source": "arxiv" }, { "paper_id": "arxiv:1503.05432", "title": "Discrete Signal Processing on Graphs: Sampling Theory", "citation_count": 664, "source": "arxiv" }, { "paper_id": "arxiv:0704.1269", "title": "Phase transitions in the coloring of random graphs", "citation_count": 303, "source": "arxiv" }, { "paper_id": "arxiv:1512.03547", "title": "Graph Isomorphism in Quasipolynomial Time", "citation_count": 283, "source": "arxiv" }, { "paper_id": "arxiv:1511.06773", "title": "Unifying and Strengthening Hardness for Dynamic Problems via the Online Matrix-Vector Multiplication Conjecture", "citation_count": 221, "source": "arxiv" } ] }, { "id": 11, "size": 12646, "top_tags": [ { "tag": "autonomous driving", "n": 606 }, { "tag": "computer vision", "n": 552 }, { "tag": "RGB", "n": 541 }, { "tag": "deep learning", "n": 382 }, { "tag": "LiDAR", "n": 359 }, { "tag": "3d object detection", "n": 351 }, { "tag": "NeRF", "n": 345 }, { "tag": "view synthesis", "n": 340 } ], "top_papers": [ { "paper_id": "arxiv:1312.4659", "title": "DeepPose: Human Pose Estimation via Deep Neural Networks", "citation_count": 3238, "source": "arxiv" }, { "paper_id": "arxiv:1512.03012", "title": "ShapeNet: An Information-Rich 3D Model Repository", "citation_count": 2373, "source": "arxiv" }, { "paper_id": "arxiv:1512.02134", "title": "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation", "citation_count": 2174, "source": "arxiv" }, { "paper_id": "arxiv:1406.2283", "title": "Depth Map Prediction from a Single Image using a Multi-Scale Deep Network", "citation_count": 1844, "source": "arxiv" }, { "paper_id": "arxiv:1905.04757", "title": "NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding", "citation_count": 1713, "source": "arxiv" } ] }, { "id": 56, "size": 12565, "top_tags": [ { "tag": "machine learning", "n": 1259 }, { "tag": "training data", "n": 730 }, { "tag": "unlabeled data", "n": 507 }, { "tag": "active learning", "n": 451 }, { "tag": "machine learning models", "n": 431 }, { "tag": "ML", "n": 361 }, { "tag": "target domain", "n": 361 }, { "tag": "semi - supervised learning", "n": 343 } ], "top_papers": [ { "paper_id": "arxiv:1201.0490", "title": "Scikit-learn: Machine Learning in Python", "citation_count": 63659, "source": "arxiv" }, { "paper_id": "arxiv:1106.1813", "title": "SMOTE: Synthetic Minority Over-sampling Technique", "citation_count": 30787, "source": "arxiv" }, { "paper_id": "arxiv:1703.05175", "title": "Prototypical Networks for Few-shot Learning", "citation_count": 5192, "source": "arxiv" }, { "paper_id": "arxiv:2010.16061", "title": "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation", "citation_count": 4430, "source": "arxiv" }, { "paper_id": "arxiv:1106.0257", "title": "Popular Ensemble Methods: An Empirical Study", "citation_count": 2965, "source": "arxiv" } ] }, { "id": 62, "size": 12535, "top_tags": [ { "tag": "language models", "n": 1630 }, { "tag": "CLIP", "n": 622 }, { "tag": "VQA", "n": 492 }, { "tag": "computer vision", "n": 440 }, { "tag": "visual question", "n": 414 }, { "tag": "language model", "n": 398 }, { "tag": "image captioning", "n": 371 }, { "tag": "multimodal large language models", "n": 361 } ], "top_papers": [ { "paper_id": "arxiv:2103.00020", "title": "Learning Transferable Visual Models From Natural Language Supervision", "citation_count": 5296, "source": "arxiv" }, { "paper_id": "arxiv:1807.03748", "title": "Representation Learning with Contrastive Predictive Coding", "citation_count": 4519, "source": "arxiv" }, { "paper_id": "arxiv:1212.0402", "title": "UCF-101: A dataset of 101 human actions classes from videos in the wild", "citation_count": 4445, "source": "arxiv" }, { "paper_id": "arxiv:1405.0312", "title": "Microsoft COCO: Common Objects in Context", "citation_count": 2354, "source": "arxiv" }, { "paper_id": "arxiv:2204.06125", "title": "Hierarchical Text-Conditional Image Generation with CLIP Latents", "citation_count": 2278, "source": "arxiv" } ] }, { "id": 27, "size": 12185, "top_tags": [ { "tag": "quantum computing", "n": 1373 }, { "tag": "quantum computers", "n": 1129 }, { "tag": "quantum algorithms", "n": 1012 }, { "tag": "quantum circuits", "n": 813 }, { "tag": "quantum computation", "n": 742 }, { "tag": "quantum computer", "n": 653 }, { "tag": "quantum algorithm", "n": 599 }, { "tag": "quantum states", "n": 398 } ], "top_papers": [ { "paper_id": "arxiv:1910.11333", "title": "Quantum supremacy using a programmable superconducting processor", "citation_count": 6935, "source": "arxiv" }, { "paper_id": "arxiv:1304.3061", "title": "A variational eigenvalue solver on a photonic quantum processor", "citation_count": 4515, "source": "arxiv" }, { "paper_id": "arxiv:1208.0928", "title": "Surface codes: Towards practical large-scale quantum computation", "citation_count": 3008, "source": "arxiv" }, { "paper_id": "arxiv:1302.5843", "title": "Ising formulations of many NP problems", "citation_count": 2428, "source": "arxiv" }, { "paper_id": "arxiv:1509.04279", "title": "The theory of variational hybrid quantum-classical algorithms", "citation_count": 2231, "source": "arxiv" } ] }, { "id": 26, "size": 11550, "top_tags": [ { "tag": "language models", "n": 2309 }, { "tag": "natural language processing", "n": 962 }, { "tag": "LLMs", "n": 845 }, { "tag": "NLP", "n": 698 }, { "tag": "BERT", "n": 689 }, { "tag": "entity recognition", "n": 486 }, { "tag": "LLM", "n": 486 }, { "tag": "language model", "n": 455 } ], "top_papers": [ { "paper_id": "arxiv:1301.3781", "title": "Efficient Estimation of Word Representations in Vector Space", "citation_count": 18123, "source": "arxiv" }, { "paper_id": "arxiv:1103.0398", "title": "Natural Language Processing (almost) from Scratch", "citation_count": 5181, "source": "arxiv" }, { "paper_id": "arxiv:1405.4053", "title": "Distributed Representations of Sentences and Documents", "citation_count": 5119, "source": "arxiv" }, { "paper_id": "arxiv:1910.10683", "title": "Exploring the Limits of Transfer Learning with a Unified Text-to-Text\\n Transformer", "citation_count": 3692, "source": "arxiv" }, { "paper_id": "arxiv:1904.09675", "title": "BERTScore: Evaluating Text Generation with BERT", "citation_count": 2036, "source": "arxiv" } ] }, { "id": 12, "size": 10631, "top_tags": [ { "tag": "neural networks", "n": 2561 }, { "tag": "deep neural networks", "n": 1748 }, { "tag": "deep learning", "n": 1337 }, { "tag": "neural network", "n": 908 }, { "tag": "machine learning", "n": 532 }, { "tag": "gradient descent", "n": 430 }, { "tag": "SGD", "n": 391 }, { "tag": "stochastic gradient descent", "n": 371 } ], "top_papers": [ { "paper_id": "arxiv:1412.6980", "title": "Adam: A Method for Stochastic Optimization", "citation_count": 84666, "source": "arxiv" }, { "paper_id": "arxiv:1502.03167", "title": "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift", "citation_count": 24342, "source": "arxiv" }, { "paper_id": "arxiv:1608.03981", "title": "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising", "citation_count": 8741, "source": "arxiv" }, { "paper_id": "arxiv:1207.0580", "title": "Improving neural networks by preventing co-adaptation of feature detectors", "citation_count": 6651, "source": "arxiv" }, { "paper_id": "arxiv:1312.6199", "title": "Intriguing properties of neural networks", "citation_count": 5724, "source": "arxiv" } ] }, { "id": 4, "size": 10547, "top_tags": [ { "tag": "finite fields", "n": 619 }, { "tag": "finite field", "n": 558 }, { "tag": "math xmlns", "n": 209 }, { "tag": "MathML", "n": 202 }, { "tag": "positive integer", "n": 191 }, { "tag": "sufficient conditions", "n": 160 }, { "tag": "lower bounds", "n": 135 }, { "tag": "elliptic curves", "n": 126 } ], "top_papers": [ { "paper_id": "arxiv:1004.3348", "title": "ON MUTUALLY UNBIASED BASES", "citation_count": 736, "source": "arxiv" }, { "paper_id": "arxiv:1401.7714", "title": "Algebraic complexity theory and matrix multiplication", "citation_count": 209, "source": "arxiv" }, { "paper_id": "arxiv:1411.0911", "title": "Reducing differential equations for multiloop master integrals", "citation_count": 201, "source": "arxiv" }, { "paper_id": "arxiv:1511.01071", "title": "Integration-by-parts reductions from unitarity cuts and algebraic geometry", "citation_count": 193, "source": "arxiv" }, { "paper_id": "arxiv:1107.5665", "title": "Dualities in persistent (co)homology", "citation_count": 161, "source": "arxiv" } ] }, { "id": 22, "size": 9995, "top_tags": [ { "tag": "reinforcement learning", "n": 3921 }, { "tag": "RL", "n": 2921 }, { "tag": "deep reinforcement learning", "n": 1111 }, { "tag": "offline reinforcement learning", "n": 410 }, { "tag": "reward function", "n": 378 }, { "tag": "imitation learning", "n": 351 }, { "tag": "optimal policy", "n": 348 }, { "tag": "sample efficiency", "n": 345 } ], "top_papers": [ { "paper_id": "arxiv:1707.06347", "title": "Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper)", "citation_count": 11298, "source": "arxiv" }, { "paper_id": "arxiv:1509.02971", "title": "Continuous control with deep reinforcement learning", "citation_count": 5371, "source": "arxiv" }, { "paper_id": "arxiv:1312.5602", "title": "Playing Atari with Deep Reinforcement Learning", "citation_count": 5121, "source": "arxiv" }, { "paper_id": "arxiv:1509.06461", "title": "Deep Reinforcement Learning with Double Q-Learning", "citation_count": 3520, "source": "arxiv" }, { "paper_id": "arxiv:1801.01290", "title": "Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor", "citation_count": 3493, "source": "arxiv" } ] }, { "id": 28, "size": 9942, "top_tags": [ { "tag": "blockchain technology", "n": 383 }, { "tag": "smart contracts", "n": 372 }, { "tag": "IoT", "n": 294 }, { "tag": "iot devices", "n": 242 }, { "tag": "cloud computing", "n": 228 }, { "tag": "mobile devices", "n": 161 }, { "tag": "sensitive data", "n": 138 }, { "tag": "security issues", "n": 127 } ], "top_papers": [ { "paper_id": "arxiv:1906.11078", "title": "Blockchain technology overview", "citation_count": 1491, "source": "arxiv" }, { "paper_id": "arxiv:1505.07919", "title": "A Survey on Wireless Security: Technical Challenges, Recent Advances, and Future Trends", "citation_count": 1221, "source": "arxiv" }, { "paper_id": "arxiv:1407.3561", "title": "A Privacy-Preserving and Transparent Certification System for Digital Credentials", "citation_count": 1206, "source": "arxiv" }, { "paper_id": "arxiv:2203.02662", "title": "A Survey on Metaverse: Fundamentals, Security, and Privacy", "citation_count": 1205, "source": "arxiv" }, { "paper_id": "arxiv:1706.00916", "title": "A Survey on Security and Privacy Issues of Bitcoin", "citation_count": 1070, "source": "arxiv" } ] }, { "id": 1, "size": 9918, "top_tags": [ { "tag": "generative adversarial networks", "n": 1451 }, { "tag": "GAN", "n": 1434 }, { "tag": "diffusion models", "n": 832 }, { "tag": "generative models", "n": 755 }, { "tag": "image generation", "n": 547 }, { "tag": "deep learning", "n": 457 }, { "tag": "latent space", "n": 400 }, { "tag": "generative adversarial network", "n": 400 } ], "top_papers": [ { "paper_id": "arxiv:1411.1784", "title": "Conditional Generative Adversarial Nets", "citation_count": 8899, "source": "arxiv" }, { "paper_id": "arxiv:1511.06434", "title": "Unsupervised Representation Learning with Deep Convolutional Generative\\n Adversarial Networks", "citation_count": 6993, "source": "arxiv" }, { "paper_id": "arxiv:1710.07035", "title": "Generative Adversarial Networks: An Overview", "citation_count": 4394, "source": "arxiv" }, { "paper_id": "arxiv:1706.08500", "title": "GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium", "citation_count": 3814, "source": "arxiv" }, { "paper_id": "arxiv:1601.07661", "title": "DehazeNet: An End-to-End System for Single Image Haze Removal", "citation_count": 3225, "source": "arxiv" } ] }, { "id": 23, "size": 9503, "top_tags": [ { "tag": "ASR", "n": 813 }, { "tag": "automatic speech recognition", "n": 693 }, { "tag": "deep learning", "n": 447 }, { "tag": "speech recognition", "n": 401 }, { "tag": "speech enhancement", "n": 362 }, { "tag": "TTS", "n": 310 }, { "tag": "deep neural networks", "n": 289 }, { "tag": "speech synthesis", "n": 253 } ], "top_papers": [ { "paper_id": "arxiv:1412.3555", "title": "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling", "citation_count": 10784, "source": "arxiv" }, { "paper_id": "arxiv:1609.03499", "title": "WaveNet: A Generative Model for Raw Audio", "citation_count": 3610, "source": "arxiv" }, { "paper_id": "arxiv:1904.08779", "title": "SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition", "citation_count": 3512, "source": "arxiv" }, { "paper_id": "arxiv:1806.05622", "title": "VoxCeleb2: Deep Speaker Recognition", "citation_count": 2245, "source": "arxiv" }, { "paper_id": "arxiv:1706.08612", "title": "VoxCeleb: A Large-Scale Speaker Identification Dataset", "citation_count": 2122, "source": "arxiv" } ] }, { "id": 52, "size": 9443, "top_tags": [ { "tag": "machine learning", "n": 476 }, { "tag": "objective function", "n": 328 }, { "tag": "SGD", "n": 315 }, { "tag": "stochastic gradient descent", "n": 307 }, { "tag": "optimization problems", "n": 258 }, { "tag": "convergence rate", "n": 247 }, { "tag": "gradient descent", "n": 221 }, { "tag": "optimization problem", "n": 200 } ], "top_papers": [ { "paper_id": "arxiv:1609.04747", "title": "An overview of gradient descent optimization algorithms", "citation_count": 4795, "source": "arxiv" }, { "paper_id": "arxiv:0912.3995", "title": "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design", "citation_count": 1052, "source": "arxiv" }, { "paper_id": "arxiv:1005.2012", "title": "Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling", "citation_count": 899, "source": "arxiv" }, { "paper_id": "arxiv:1307.5561", "title": "On the Linear Convergence of the ADMM in Decentralized Consensus Optimization", "citation_count": 857, "source": "arxiv" }, { "paper_id": "arxiv:1604.00772", "title": "The CMA Evolution Strategy: A Tutorial", "citation_count": 617, "source": "arxiv" } ] }, { "id": 44, "size": 9296, "top_tags": [ { "tag": "computer vision", "n": 356 }, { "tag": "image processing", "n": 257 }, { "tag": "face recognition", "n": 225 }, { "tag": "experimental results", "n": 216 }, { "tag": "image segmentation", "n": 174 }, { "tag": "machine learning", "n": 125 }, { "tag": "MRI", "n": 108 }, { "tag": "image quality", "n": 107 } ], "top_papers": [ { "paper_id": "arxiv:1802.03426", "title": "UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction", "citation_count": 7495, "source": "arxiv" }, { "paper_id": "arxiv:1404.7584", "title": "High-Speed Tracking with Kernelized Correlation Filters", "citation_count": 5782, "source": "arxiv" }, { "paper_id": "arxiv:1602.00763", "title": "Simple online and realtime tracking", "citation_count": 3857, "source": "arxiv" }, { "paper_id": "arxiv:1012.1184", "title": "Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization", "citation_count": 1107, "source": "arxiv" }, { "paper_id": "arxiv:2104.13015", "title": "Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding", "citation_count": 916, "source": "arxiv" } ] }, { "id": 58, "size": 9269, "top_tags": [ { "tag": "quantum states", "n": 779 }, { "tag": "quantum information", "n": 443 }, { "tag": "quantum state", "n": 413 }, { "tag": "quantum channels", "n": 391 }, { "tag": "quantum correlations", "n": 377 }, { "tag": "classical communication", "n": 374 }, { "tag": "entangled states", "n": 352 }, { "tag": "quantum mechanics", "n": 344 } ], "top_papers": [ { "paper_id": "arxiv:2003.06557", "title": "Quantum cryptography: Public key distribution and coin tossing", "citation_count": 5384, "source": "arxiv" }, { "paper_id": "arxiv:1906.01645", "title": "Advances in quantum cryptography", "citation_count": 1735, "source": "arxiv" }, { "paper_id": "arxiv:0908.0238", "title": "Measure for the Degree of Non-Markovian Behavior of Quantum Processes in Open Systems", "citation_count": 1465, "source": "arxiv" }, { "paper_id": "arxiv:1302.3428", "title": "Quantum error correction for quantum memories", "citation_count": 1345, "source": "arxiv" }, { "paper_id": "arxiv:1004.0190", "title": "Necessary and Sufficient Condition for Nonzero Quantum Discord", "citation_count": 1198, "source": "arxiv" } ] }, { "id": 57, "size": 9120, "top_tags": [ { "tag": "EEG", "n": 717 }, { "tag": "MRI", "n": 331 }, { "tag": "neural activity", "n": 299 }, { "tag": "human brain", "n": 247 }, { "tag": "brain regions", "n": 244 }, { "tag": "neural mechanisms", "n": 211 }, { "tag": "brain activity", "n": 197 }, { "tag": "functional connectivity", "n": 166 } ], "top_papers": [ { "paper_id": "arxiv:1511.06448", "title": "Learning Representations from EEG with Deep Recurrent-Convolutional\\n Neural Networks", "citation_count": 543, "source": "arxiv" }, { "paper_id": "arxiv:1502.06172", "title": "Clique topology reveals intrinsic geometric structure in neural correlations", "citation_count": 399, "source": "arxiv" }, { "paper_id": "arxiv:1608.03425", "title": "Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision", "citation_count": 327, "source": "arxiv" }, { "paper_id": "arxiv:1901.08644", "title": "Ablation Studies in Artificial Neural Networks", "citation_count": 171, "source": "arxiv" }, { "paper_id": "arxiv:2101.08123", "title": "Technological Competence Is a Pre-condition for Effective Implementation of Virtual Reality Head Mounted Displays in Human Neuroscience: A Technological Review and Meta-Analysis", "citation_count": 167, "source": "arxiv" } ] }, { "id": 18, "size": 8847, "top_tags": [ { "tag": "gaussian processes", "n": 506 }, { "tag": "diffusion models", "n": 439 }, { "tag": "GP", "n": 388 }, { "tag": "variational inference", "n": 332 }, { "tag": "gaussian process", "n": 332 }, { "tag": "machine learning", "n": 324 }, { "tag": "bayesian inference", "n": 303 }, { "tag": "generative models", "n": 273 } ], "top_papers": [ { "paper_id": "arxiv:1206.2944", "title": "Practical Bayesian Optimization of Machine Learning Algorithms", "citation_count": 5659, "source": "arxiv" }, { "paper_id": "arxiv:1601.00670", "title": "Variational Inference: A Review for Statisticians", "citation_count": 3674, "source": "arxiv" }, { "paper_id": "arxiv:1302.4964", "title": "Estimating Continuous Distributions in Bayesian Classifiers", "citation_count": 2922, "source": "arxiv" }, { "paper_id": "arxiv:1406.5823", "title": "Fitting Linear Mixed-Effects Models Using lme4", "citation_count": 2577, "source": "arxiv" }, { "paper_id": "arxiv:1906.02691", "title": "An Introduction to Variational Autoencoders", "citation_count": 2469, "source": "arxiv" } ] }, { "id": 34, "size": 8493, "top_tags": [ { "tag": "order logic", "n": 313 }, { "tag": "regular languages", "n": 185 }, { "tag": "natural numbers", "n": 165 }, { "tag": "NP", "n": 125 }, { "tag": "infinite words", "n": 119 }, { "tag": "type theory", "n": 105 }, { "tag": "modal logic", "n": 104 }, { "tag": "finite automata", "n": 100 } ], "top_papers": [ { "paper_id": "arxiv:1308.0729", "title": "A Homological Theory of Functions: Nonuniform Boolean Complexity Separation and VC Dimension Bound Via Algebraic Topology, and a Homological Farkas Lemma", "citation_count": 385, "source": "arxiv" }, { "paper_id": "arxiv:2305.00968", "title": "The Monadic Theory of Order", "citation_count": 323, "source": "arxiv" }, { "paper_id": "arxiv:1312.1399", "title": "Handling Algebraic Effects", "citation_count": 138, "source": "arxiv" }, { "paper_id": "arxiv:0705.2205", "title": "From Nondeterministic B\\\"uchi and Streett Automata to Deterministic Parity Automata", "citation_count": 129, "source": "arxiv" }, { "paper_id": "arxiv:1303.3255", "title": "Sheaves, Cosheaves and Applications", "citation_count": 115, "source": "arxiv" } ] }, { "id": 14, "size": 8440, "top_tags": [ { "tag": "CI", "n": 1189 }, { "tag": "% ci", "n": 1121 }, { "tag": "systematic review", "n": 375 }, { "tag": "OR", "n": 294 }, { "tag": "AI", "n": 286 }, { "tag": "HR", "n": 244 }, { "tag": "UK", "n": 212 }, { "tag": "older adults", "n": 208 } ], "top_papers": [ { "paper_id": "arxiv:2012.12028", "title": "Wiley StatsRef: Statistics Reference Online", "citation_count": 780, "source": "arxiv" }, { "paper_id": "arxiv:1407.5296", "title": "An investigation of the false discovery rate and the misinterpretation of p -values", "citation_count": 708, "source": "arxiv" }, { "paper_id": "arxiv:2301.12591", "title": "Cybersickness in Virtual Reality Questionnaire (CSQ-VR): A Validation and Comparison against SSQ and VRSQ", "citation_count": 140, "source": "arxiv" }, { "paper_id": "arxiv:2004.09545", "title": "Influence of COVID-19 confinement in students performance in higher education", "citation_count": 119, "source": "arxiv" }, { "paper_id": "arxiv:1206.6840", "title": "Direct and Indirect Effects of Sequential Treatments", "citation_count": 97, "source": "arxiv" } ] }, { "id": 7, "size": 8356, "top_tags": [ { "tag": "GPU", "n": 659 }, { "tag": "CPU", "n": 376 }, { "tag": "HPC", "n": 300 }, { "tag": "FPGA", "n": 255 }, { "tag": "performance computing", "n": 250 }, { "tag": "DRAM", "n": 162 }, { "tag": "MPI", "n": 154 }, { "tag": "energy consumption", "n": 145 } ], "top_papers": [ { "paper_id": "arxiv:1102.1523", "title": "The NumPy Array: A Structure for Efficient Numerical Computation", "citation_count": 11008, "source": "arxiv" }, { "paper_id": "arxiv:2006.11477", "title": "In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication", "citation_count": 2444, "source": "arxiv" }, { "paper_id": "arxiv:2006.09167", "title": "Heterogeneous parallelization and acceleration of molecular dynamics simulations in GROMACS", "citation_count": 859, "source": "arxiv" }, { "paper_id": "arxiv:1209.5145", "title": "Julia: A Fast Dynamic Language for Technical Computing", "citation_count": 669, "source": "arxiv" }, { "paper_id": "arxiv:1507.04072", "title": "Journal of the Korean Physical Society", "citation_count": 595, "source": "arxiv" } ] }, { "id": 13, "size": 8309, "top_tags": [ { "tag": "adversarial attacks", "n": 1714 }, { "tag": "adversarial examples", "n": 1496 }, { "tag": "deep neural networks", "n": 1386 }, { "tag": "adversarial training", "n": 721 }, { "tag": "deep learning", "n": 716 }, { "tag": "machine learning", "n": 647 }, { "tag": "neural networks", "n": 643 }, { "tag": "adversarial robustness", "n": 595 } ], "top_papers": [ { "paper_id": "arxiv:1412.6572", "title": "Explaining and Harnessing Adversarial Examples", "citation_count": 8131, "source": "arxiv" }, { "paper_id": "arxiv:1710.09412", "title": "mixup: Beyond Empirical Risk Minimization", "citation_count": 4752, "source": "arxiv" }, { "paper_id": "arxiv:1607.02533", "title": "Adversarial Examples in the Physical World", "citation_count": 1852, "source": "arxiv" }, { "paper_id": "arxiv:1704.01155", "title": "Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks", "citation_count": 1839, "source": "arxiv" }, { "paper_id": "arxiv:1708.03999", "title": "ZOO", "citation_count": 1740, "source": "arxiv" } ] }, { "id": 55, "size": 8182, "top_tags": [ { "tag": "language models", "n": 5487 }, { "tag": "LLMs", "n": 3363 }, { "tag": "LLM", "n": 1744 }, { "tag": "language model", "n": 611 }, { "tag": "AI", "n": 568 }, { "tag": "reinforcement learning", "n": 328 }, { "tag": "natural language", "n": 285 }, { "tag": "GPT-4", "n": 274 } ], "top_papers": [ { "paper_id": "arxiv:1810.04805", "title": "AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale", "citation_count": 45574, "source": "arxiv" }, { "paper_id": "arxiv:1907.11692", "title": "HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case", "citation_count": 17296, "source": "arxiv" }, { "paper_id": "arxiv:2203.02155", "title": "Training language models to follow instructions with human feedback", "citation_count": 4280, "source": "arxiv" }, { "paper_id": "arxiv:2201.11903", "title": "BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence", "citation_count": 4245, "source": "arxiv" }, { "paper_id": "arxiv:2303.18223", "title": "A Survey of Large Language Models", "citation_count": 1398, "source": "arxiv" } ] }, { "id": 50, "size": 7859, "top_tags": [ { "tag": "wireless sensor networks", "n": 426 }, { "tag": "IoT", "n": 295 }, { "tag": "SDN", "n": 290 }, { "tag": "wireless networks", "n": 287 }, { "tag": "energy consumption", "n": 278 }, { "tag": "cloud computing", "n": 272 }, { "tag": "MEC", "n": 232 }, { "tag": "mobile devices", "n": 231 } ], "top_papers": [ { "paper_id": "arxiv:0803.0952", "title": "Femtocell networks: a survey", "citation_count": 3056, "source": "arxiv" }, { "paper_id": "arxiv:1702.05309", "title": "Mobile Edge Computing: A Survey on Architecture and Computation Offloading", "citation_count": 2936, "source": "arxiv" }, { "paper_id": "arxiv:0901.0131", "title": "Cloud Computing and Grid Computing 360-Degree Compared", "citation_count": 2910, "source": "arxiv" }, { "paper_id": "arxiv:1305.0982", "title": "Context Aware Computing for The Internet of Things: A Survey", "citation_count": 2770, "source": "arxiv" }, { "paper_id": "arxiv:1603.08462", "title": "Survey of Important Issues in UAV Communication Networks", "citation_count": 2294, "source": "arxiv" } ] }, { "id": 43, "size": 7731, "top_tags": [ { "tag": "deep neural networks", "n": 1167 }, { "tag": "deep learning", "n": 971 }, { "tag": "neural networks", "n": 706 }, { "tag": "convolutional neural networks", "n": 524 }, { "tag": "DNN", "n": 516 }, { "tag": "CNN", "n": 431 }, { "tag": "neural architecture search", "n": 380 }, { "tag": "GPU", "n": 373 } ], "top_papers": [ { "paper_id": "arxiv:1912.01703", "title": "PyTorch: An Imperative Style, High-Performance Deep Learning Library", "citation_count": 16187, "source": "arxiv" }, { "paper_id": "arxiv:1503.02531", "title": "Distilling the Knowledge in a Neural Network", "citation_count": 13936, "source": "arxiv" }, { "paper_id": "arxiv:1603.04467", "title": "TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems", "citation_count": 9771, "source": "arxiv" }, { "paper_id": "arxiv:1605.08695", "title": "TensorFlow: A system for large-scale machine learning", "citation_count": 8814, "source": "arxiv" }, { "paper_id": "arxiv:1804.02767", "title": "YOLOv3: An Incremental Improvement", "citation_count": 5887, "source": "arxiv" } ] }, { "id": 59, "size": 7675, "top_tags": [ { "tag": "order logic", "n": 313 }, { "tag": "SAT", "n": 255 }, { "tag": "logic programming", "n": 203 }, { "tag": "ASP", "n": 199 }, { "tag": "programming languages", "n": 180 }, { "tag": "logic programs", "n": 169 }, { "tag": "answer set programming", "n": 139 }, { "tag": "SMT", "n": 137 } ], "top_papers": [ { "paper_id": "arxiv:1107.0023", "title": "CP-nets: A Tool for Representing and Reasoning withConditional Ceteris Paribus Preference Statements", "citation_count": 878, "source": "arxiv" }, { "paper_id": "arxiv:1106.0667", "title": "Reasoning within Fuzzy Description Logics", "citation_count": 526, "source": "arxiv" }, { "paper_id": "arxiv:2105.06319", "title": "The inductive approach to verifying cryptographic protocols", "citation_count": 504, "source": "arxiv" }, { "paper_id": "arxiv:1811.04211", "title": "Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs", "citation_count": 426, "source": "arxiv" }, { "paper_id": "arxiv:1106.1819", "title": "A Knowledge Compilation Map", "citation_count": 379, "source": "arxiv" } ] }, { "id": 51, "size": 7639, "top_tags": [ { "tag": "graph neural networks", "n": 2119 }, { "tag": "GNN", "n": 896 }, { "tag": "graph neural network", "n": 342 }, { "tag": "node classification", "n": 310 }, { "tag": "link prediction", "n": 308 }, { "tag": "graph structure", "n": 305 }, { "tag": "graph convolutional networks", "n": 298 }, { "tag": "graph representation learning", "n": 277 } ], "top_papers": [ { "paper_id": "arxiv:1901.00596", "title": "A Comprehensive Survey on Graph Neural Networks", "citation_count": 9052, "source": "arxiv" }, { "paper_id": "arxiv:1403.6652", "title": "DeepWalk", "citation_count": 8486, "source": "arxiv" }, { "paper_id": "arxiv:1609.02907", "title": "Semi-Supervised Classification with Graph Convolutional Networks", "citation_count": 8068, "source": "arxiv" }, { "paper_id": "arxiv:1503.03578", "title": "LINE", "citation_count": 4684, "source": "arxiv" }, { "paper_id": "arxiv:1806.01973", "title": "Graph Convolutional Neural Networks for Web-Scale Recommender Systems", "citation_count": 2740, "source": "arxiv" } ] }, { "id": 2, "size": 7595, "top_tags": [ { "tag": "bayesian networks", "n": 329 }, { "tag": "random variables", "n": 258 }, { "tag": "graphical models", "n": 201 }, { "tag": "probability distributions", "n": 200 }, { "tag": "causal discovery", "n": 187 }, { "tag": "causal inference", "n": 180 }, { "tag": "observational data", "n": 172 }, { "tag": "machine learning", "n": 157 } ], "top_papers": [ { "paper_id": "arxiv:1101.1438", "title": "Optimal Detection of Changepoints With a Linear Computational Cost", "citation_count": 2434, "source": "arxiv" }, { "paper_id": "arxiv:1301.2294", "title": "Expectation Propagation for approximate Bayesian inference", "citation_count": 1466, "source": "arxiv" }, { "paper_id": "arxiv:1301.6725", "title": "Loopy Belief Propagation for Approximate Inference: An Empirical Study", "citation_count": 1465, "source": "arxiv" }, { "paper_id": "arxiv:1709.01449", "title": "Visualization in Bayesian Workflow", "citation_count": 1119, "source": "arxiv" }, { "paper_id": "arxiv:1312.2372", "title": "Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter", "citation_count": 744, "source": "arxiv" } ] }, { "id": 19, "size": 7566, "top_tags": [ { "tag": "language models", "n": 2149 }, { "tag": "LLMs", "n": 765 }, { "tag": "neural machine translation", "n": 620 }, { "tag": "natural language processing", "n": 420 }, { "tag": "NMT", "n": 405 }, { "tag": "LLM", "n": 373 }, { "tag": "recurrent neural networks", "n": 358 }, { "tag": "language model", "n": 342 } ], "top_papers": [ { "paper_id": "arxiv:1409.0473", "title": "Neural Machine Translation by Jointly Learning to Align and Translate", "citation_count": 14596, "source": "arxiv" }, { "paper_id": "arxiv:1409.3215", "title": "Sequence to Sequence Learning with Neural Networks", "citation_count": 13340, "source": "arxiv" }, { "paper_id": "arxiv:1503.04069", "title": "LSTM: A Search Space Odyssey", "citation_count": 6776, "source": "arxiv" }, { "paper_id": "arxiv:1706.03762", "title": "Attention Is All You Need", "citation_count": 6551, "source": "arxiv" }, { "paper_id": "arxiv:1609.08144", "title": "Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation", "citation_count": 5661, "source": "arxiv" } ] }, { "id": 32, "size": 7333, "top_tags": [ { "tag": "bounded domain", "n": 243 }, { "tag": "asymptotic behavior", "n": 170 }, { "tag": "boundary conditions", "n": 151 }, { "tag": "dirichlet problem", "n": 137 }, { "tag": "sufficient conditions", "n": 131 }, { "tag": "math xmlns", "n": 129 }, { "tag": "weak solutions", "n": 122 }, { "tag": "dirichlet boundary conditions", "n": 114 } ], "top_papers": [ { "paper_id": "arxiv:1204.6216", "title": "Geodesics in heat", "citation_count": 401, "source": "arxiv" }, { "paper_id": "arxiv:0906.4325", "title": "Finite element exterior calculus: from Hodge theory to numerical stability", "citation_count": 395, "source": "arxiv" }, { "paper_id": "arxiv:1203.0908", "title": "An optimal error estimate in stochastic homogenization of discrete elliptic equations", "citation_count": 209, "source": "arxiv" }, { "paper_id": "arxiv:0901.3261", "title": "From the long jump random walk to the fractional Laplacian", "citation_count": 203, "source": "arxiv" }, { "paper_id": "arxiv:1104.1291", "title": "An optimal variance estimate in stochastic homogenization of discrete elliptic equations", "citation_count": 164, "source": "arxiv" } ] }, { "id": 3, "size": 7293, "top_tags": [ { "tag": "language models", "n": 883 }, { "tag": "LLMs", "n": 618 }, { "tag": "source code", "n": 490 }, { "tag": "software engineering", "n": 432 }, { "tag": "software development", "n": 415 }, { "tag": "LLM", "n": 380 }, { "tag": "code generation", "n": 244 }, { "tag": "software systems", "n": 243 } ], "top_papers": [ { "paper_id": "arxiv:1801.02634", "title": "The Astropy Project: Building an Open-science Project and Status of the v2.0 Core Package*", "citation_count": 7225, "source": "arxiv" }, { "paper_id": "arxiv:2303.08774", "title": "GPT-4 Technical Report", "citation_count": 2335, "source": "arxiv" }, { "paper_id": "arxiv:1309.0238", "title": "API design for machine learning software: experiences from the scikit-learn project", "citation_count": 1801, "source": "arxiv" }, { "paper_id": "arxiv:1605.02688", "title": "Static Analysis of Shape in TensorFlow Programs", "citation_count": 1684, "source": "arxiv" }, { "paper_id": "arxiv:2107.03374", "title": "Evaluating Large Language Models Trained on Code", "citation_count": 1423, "source": "arxiv" } ] }, { "id": 35, "size": 7227, "top_tags": [ { "tag": "knowledge graphs", "n": 239 }, { "tag": "information retrieval", "n": 230 }, { "tag": "data mining", "n": 204 }, { "tag": "RDF", "n": 198 }, { "tag": "knowledge graph", "n": 161 }, { "tag": "big data", "n": 150 }, { "tag": "search engines", "n": 148 }, { "tag": "machine learning", "n": 148 } ], "top_papers": [ { "paper_id": "arxiv:1603.02754", "title": "XGBoost", "citation_count": 47531, "source": "arxiv" }, { "paper_id": "arxiv:1508.01991", "title": "Bidirectional LSTM-CRF Models for Sequence Tagging", "citation_count": 3284, "source": "arxiv" }, { "paper_id": "arxiv:1105.5444", "title": "Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language", "citation_count": 2085, "source": "arxiv" }, { "paper_id": "arxiv:1510.04389", "title": "Sketch-based manga retrieval using manga109 dataset", "citation_count": 1372, "source": "arxiv" }, { "paper_id": "arxiv:1611.09268", "title": "Analysis of Points of Interests Recommended for Leisure Walk Descriptions", "citation_count": 1289, "source": "arxiv" } ] }, { "id": 40, "size": 7097, "top_tags": [ { "tag": "LDPC", "n": 505 }, { "tag": "polar codes", "n": 378 }, { "tag": "density parity", "n": 341 }, { "tag": "linear codes", "n": 328 }, { "tag": "minimum distance", "n": 328 }, { "tag": "ldpc codes", "n": 253 }, { "tag": "MathML", "n": 251 }, { "tag": "MDS", "n": 248 } ], "top_papers": [ { "paper_id": "arxiv:0807.3917", "title": "Channel Polarization: A Method for Constructing Capacity-Achieving Codes for Symmetric Binary-Input Memoryless Channels", "citation_count": 4391, "source": "arxiv" }, { "paper_id": "arxiv:0711.0708", "title": "A Rank-Metric Approach to Error Control in Random Network Coding", "citation_count": 699, "source": "arxiv" }, { "paper_id": "arxiv:1401.3753", "title": "LLR-Based Successive Cancellation List Decoding of Polar Codes", "citation_count": 614, "source": "arxiv" }, { "paper_id": "arxiv:1311.3284", "title": "A Family of Optimal Locally Recoverable Codes", "citation_count": 600, "source": "arxiv" }, { "paper_id": "arxiv:1005.4178", "title": "Optimal Exact-Regenerating Codes for Distributed Storage at the MSR and MBR Points via a Product-Matrix Construction", "citation_count": 575, "source": "arxiv" } ] }, { "id": 30, "size": 6904, "top_tags": [ { "tag": "AI", "n": 490 }, { "tag": "VR", "n": 282 }, { "tag": "virtual reality", "n": 279 }, { "tag": "artificial intelligence", "n": 214 }, { "tag": "augmented reality", "n": 170 }, { "tag": "AR", "n": 143 }, { "tag": "software engineering", "n": 110 }, { "tag": "user experience", "n": 99 } ], "top_papers": [ { "paper_id": "arxiv:1709.08439", "title": "Agile Software Development Methods: Review and Analysis", "citation_count": 1193, "source": "arxiv" }, { "paper_id": "arxiv:2309.07930", "title": "Generative AI", "citation_count": 1127, "source": "arxiv" }, { "paper_id": "arxiv:1106.4869", "title": "SHOP2: An HTN Planning System", "citation_count": 933, "source": "arxiv" }, { "paper_id": "arxiv:1207.6231", "title": "Touchalytics: On the Applicability of Touchscreen Input as a Behavioral Biometric for Continuous Authentication", "citation_count": 826, "source": "arxiv" }, { "paper_id": "arxiv:2203.12687", "title": "Trust in AI and Its Role in the Acceptance of AI Technologies", "citation_count": 718, "source": "arxiv" } ] }, { "id": 29, "size": 6882, "top_tags": [ { "tag": "RNA", "n": 1012 }, { "tag": "DNA", "n": 703 }, { "tag": "gene expression", "n": 481 }, { "tag": "cell rna", "n": 236 }, { "tag": "CRISPR", "n": 193 }, { "tag": "cell types", "n": 171 }, { "tag": "transcription factors", "n": 153 }, { "tag": "molecular mechanisms", "n": 147 } ], "top_papers": [ { "paper_id": "arxiv:1110.5265", "title": "On Programs and Genomes", "citation_count": 7, "source": "arxiv" }, { "paper_id": "arxiv:1002.0065", "title": "Automated DNA Motif Discovery", "citation_count": 1, "source": "arxiv" }, { "paper_id": "arxiv:2204.14048", "title": "Topological Data Analysis in Time Series: Temporal Filtration and Application to Single-Cell Genomics", "citation_count": 1, "source": "arxiv" }, { "paper_id": "arxiv:1404.6020", "title": "A Fast Multiple Attractor Cellular Automata with Modified Clonal Classifier for Splicing Site Prediction in Human Genome", "citation_count": 0, "source": "arxiv" }, { "paper_id": "biorxiv:10.1101/2025.05.26.656218", "title": "Cohesin sumoylation is required for repression of subtelomeric gene expression in Saccharomyces cerevisiae.", "citation_count": 0, "source": "biorxiv" } ] }, { "id": 37, "size": 6721, "top_tags": [ { "tag": "sentiment analysis", "n": 726 }, { "tag": "social media", "n": 716 }, { "tag": "language models", "n": 693 }, { "tag": "natural language processing", "n": 416 }, { "tag": "LLMs", "n": 331 }, { "tag": "NLP", "n": 281 }, { "tag": "machine learning", "n": 251 }, { "tag": "hate speech", "n": 251 } ], "top_papers": [ { "paper_id": "arxiv:1509.01626", "title": "Character-level Convolutional Networks for Text Classification", "citation_count": 3277, "source": "arxiv" }, { "paper_id": "arxiv:1301.6705", "title": "Probabilistic Latent Semantic Analysis", "citation_count": 2093, "source": "arxiv" }, { "paper_id": "arxiv:1109.2128", "title": "LexRank: Graph-based Lexical Centrality as Salience in Text Summarization", "citation_count": 1637, "source": "arxiv" }, { "paper_id": "arxiv:1003.0783", "title": "Supervised Topic Models", "citation_count": 1317, "source": "arxiv" }, { "paper_id": "arxiv:2203.05794", "title": "BERTopic: Neural topic modeling with a class-based TF-IDF procedure", "citation_count": 1308, "source": "arxiv" } ] }, { "id": 8, "size": 6710, "top_tags": [ { "tag": "QKD", "n": 527 }, { "tag": "quantum key distribution", "n": 490 }, { "tag": "coherent states", "n": 250 }, { "tag": "photon pairs", "n": 240 }, { "tag": "quantum states", "n": 236 }, { "tag": "quantum communication", "n": 233 }, { "tag": "quantum information processing", "n": 210 }, { "tag": "quantum information", "n": 202 } ], "top_papers": [ { "paper_id": "arxiv:1802.04173", "title": "Topological photonics", "citation_count": 3569, "source": "arxiv" }, { "paper_id": "arxiv:2012.01625", "title": "Quantum computational advantage using photons", "citation_count": 2194, "source": "arxiv" }, { "paper_id": "arxiv:1109.1473", "title": "Measurement-Device-Independent Quantum Key Distribution", "citation_count": 2193, "source": "arxiv" }, { "paper_id": "arxiv:2005.12667", "title": "Circuit quantum electrodynamics", "citation_count": 1847, "source": "arxiv" }, { "paper_id": "arxiv:1312.1079", "title": "Interfacing single photons and single quantum dots with photonic nanostructures", "citation_count": 1425, "source": "arxiv" } ] }, { "id": 17, "size": 6636, "top_tags": [ { "tag": "lower bounds", "n": 174 }, { "tag": "multi - agent systems", "n": 157 }, { "tag": "competitive ratio", "n": 156 }, { "tag": "np -", "n": 132 }, { "tag": "NP", "n": 108 }, { "tag": "MathML", "n": 106 }, { "tag": "xlink=\"http://www.w3.org/1999", "n": 96 }, { "tag": "optimal solution", "n": 93 } ], "top_papers": [ { "paper_id": "arxiv:0802.3922", "title": "Constrained Consensus and Optimization in Multi-Agent Networks", "citation_count": 2134, "source": "arxiv" }, { "paper_id": "arxiv:1312.7377", "title": "Designing Fully Distributed Consensus Protocols for Linear Multi-Agent Systems With Directed Graphs", "citation_count": 1106, "source": "arxiv" }, { "paper_id": "arxiv:1512.02673", "title": "Speeding Up Distributed Machine Learning Using Codes", "citation_count": 866, "source": "arxiv" }, { "paper_id": "arxiv:1109.3799", "title": "Consensus of Multi-Agent Systems With General Linear and Lipschitz Nonlinear Dynamics Using Distributed Adaptive Protocols", "citation_count": 835, "source": "arxiv" }, { "paper_id": "arxiv:1012.1367", "title": "Optimal Distributed Online Prediction using Mini-Batches", "citation_count": 563, "source": "arxiv" } ] }, { "id": 10, "size": 6506, "top_tags": [ { "tag": "quantum systems", "n": 300 }, { "tag": "quantum system", "n": 242 }, { "tag": "open quantum systems", "n": 239 }, { "tag": "time evolution", "n": 188 }, { "tag": "quantum walks", "n": 180 }, { "tag": "QED", "n": 178 }, { "tag": "initial state", "n": 166 }, { "tag": "ground state", "n": 159 } ], "top_papers": [ { "paper_id": "arxiv:1308.6253", "title": "Quantum simulation", "citation_count": 2865, "source": "arxiv" }, { "paper_id": "arxiv:1904.06560", "title": "A quantum engineer's guide to superconducting qubits", "citation_count": 1829, "source": "arxiv" }, { "paper_id": "arxiv:1609.02439", "title": "Colloquium: Quantum coherence as a resource", "citation_count": 1784, "source": "arxiv" }, { "paper_id": "arxiv:1505.01385", "title": "Colloquium: Non-Markovian dynamics in open quantum systems", "citation_count": 1379, "source": "arxiv" }, { "paper_id": "arxiv:1806.06107", "title": "Quantum resource theories", "citation_count": 1282, "source": "arxiv" } ] }, { "id": 9, "size": 6487, "top_tags": [ { "tag": "t cells", "n": 560 }, { "tag": "CD8", "n": 392 }, { "tag": "RNA", "n": 333 }, { "tag": "CD4", "n": 286 }, { "tag": "DNA", "n": 212 }, { "tag": "SARS", "n": 208 }, { "tag": "CoV-2", "n": 206 }, { "tag": "CAR", "n": 182 } ], "top_papers": [ { "paper_id": "arxiv:2006.00652", "title": "In Silico Identification of Potential Natural Product Inhibitors of Human Proteases Key to SARS-CoV-2 Infection", "citation_count": 77, "source": "arxiv" }, { "paper_id": "arxiv:2312.00487", "title": "Explainable AI in Diagnosing and Anticipating Leukemia Using Transfer Learning Method", "citation_count": 67, "source": "arxiv" }, { "paper_id": "arxiv:2006.01968", "title": "Identifying Human Interactors of SARS-CoV-2 Proteins and Drug Targets for COVID-19 using Network-Based Label Propagation", "citation_count": 10, "source": "arxiv" }, { "paper_id": "arxiv:2009.01094", "title": "Computational evidence on repurposing the anti-influenza drugs baloxavir acid and baloxavir marboxil against COVID-19", "citation_count": 6, "source": "arxiv" }, { "paper_id": "arxiv:2406.02618", "title": "Immunocto: a massive immune cell database auto-generated for histopathology", "citation_count": 3, "source": "arxiv" } ] }, { "id": 48, "size": 6472, "top_tags": [ { "tag": "reinforcement learning", "n": 331 }, { "tag": "motion planning", "n": 311 }, { "tag": "language models", "n": 235 }, { "tag": "mobile robots", "n": 215 }, { "tag": "deep reinforcement learning", "n": 180 }, { "tag": "autonomous driving", "n": 179 }, { "tag": "RL", "n": 172 }, { "tag": "path planning", "n": 170 } ], "top_papers": [ { "paper_id": "arxiv:1106.4561", "title": "PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains", "citation_count": 1728, "source": "arxiv" }, { "paper_id": "arxiv:1504.00702", "title": "End-to-End Training of Deep Visuomotor Policies", "citation_count": 1399, "source": "arxiv" }, { "paper_id": "arxiv:1404.2334", "title": "Informed RRT*: Optimal sampling-based path planning focused via direct sampling of an admissible ellipsoidal heuristic", "citation_count": 1124, "source": "arxiv" }, { "paper_id": "arxiv:1710.06537", "title": "Sim-to-Real Transfer of Robotic Control with Dynamics Randomization", "citation_count": 784, "source": "arxiv" }, { "paper_id": "arxiv:1910.07113", "title": "Solving Rubik's Cube with a Robot Hand", "citation_count": 632, "source": "arxiv" } ] }, { "id": 0, "size": 6304, "top_tags": [ { "tag": "anomaly detection", "n": 886 }, { "tag": "time series", "n": 769 }, { "tag": "machine learning", "n": 466 }, { "tag": "time series data", "n": 324 }, { "tag": "deep learning", "n": 282 }, { "tag": "time series forecasting", "n": 178 }, { "tag": "ML", "n": 171 }, { "tag": "multivariate time series", "n": 169 } ], "top_papers": [ { "paper_id": "arxiv:1704.01036", "title": "Objective Criteria for the Evaluation of Clustering Methods", "citation_count": 5900, "source": "arxiv" }, { "paper_id": "arxiv:1308.0850", "title": "Generating Sequences With Recurrent Neural Networks", "citation_count": 3096, "source": "arxiv" }, { "paper_id": "arxiv:1404.1100", "title": "A Tutorial on Principal Component Analysis", "citation_count": 2270, "source": "arxiv" }, { "paper_id": "arxiv:2007.02500", "title": "Deep Learning for Anomaly Detection", "citation_count": 1734, "source": "arxiv" }, { "paper_id": "arxiv:1805.03409", "title": "N-BaIoT\u2014Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders", "citation_count": 1334, "source": "arxiv" } ] }, { "id": 49, "size": 6256, "top_tags": [ { "tag": "drug discovery", "n": 521 }, { "tag": "deep learning", "n": 406 }, { "tag": "machine learning", "n": 342 }, { "tag": "AI", "n": 314 }, { "tag": "RNA", "n": 303 }, { "tag": "language models", "n": 192 }, { "tag": "DNA", "n": 185 }, { "tag": "gene expression", "n": 162 } ], "top_papers": [ { "paper_id": "arxiv:2006.11239", "title": "Denoising Diffusion Probabilistic Models", "citation_count": 5619, "source": "arxiv" }, { "paper_id": "arxiv:1704.01212", "title": "Neural Message Passing for Quantum Chemistry", "citation_count": 2996, "source": "arxiv" }, { "paper_id": "arxiv:1801.10193", "title": "DeepDTA: deep drug\u2013target binding affinity prediction", "citation_count": 1622, "source": "arxiv" }, { "paper_id": "arxiv:1802.00543", "title": "Modeling polypharmacy side effects with graph convolutional networks", "citation_count": 1360, "source": "arxiv" }, { "paper_id": "arxiv:1711.10907", "title": "Deep reinforcement learning for de novo drug design", "citation_count": 1137, "source": "arxiv" } ] }, { "id": 33, "size": 6245, "top_tags": [ { "tag": "language models", "n": 870 }, { "tag": "natural language processing", "n": 525 }, { "tag": "machine translation", "n": 485 }, { "tag": "NLP", "n": 400 }, { "tag": "LLMs", "n": 338 }, { "tag": "resource languages", "n": 302 }, { "tag": "computational linguistics", "n": 244 }, { "tag": "MT", "n": 193 } ], "top_papers": [ { "paper_id": "arxiv:1910.03771", "title": "HuggingFace's Transformers: State-of-the-art Natural Language Processing", "citation_count": 3135, "source": "arxiv" }, { "paper_id": "arxiv:1003.1141", "title": "From Frequency to Meaning: Vector Space Models of Semantics", "citation_count": 2871, "source": "arxiv" }, { "paper_id": "arxiv:1901.07291", "title": "Cross-lingual Language Model Pretraining", "citation_count": 1620, "source": "arxiv" }, { "paper_id": "arxiv:1309.4168", "title": "Exploiting Similarities among Languages for Machine Translation", "citation_count": 1439, "source": "arxiv" }, { "paper_id": "arxiv:1104.2086", "title": "A Universal Part-of-Speech Tagset", "citation_count": 735, "source": "arxiv" } ] }, { "id": 21, "size": 6080, "top_tags": [ { "tag": "AD", "n": 706 }, { "tag": "alzheimers disease", "n": 526 }, { "tag": "PD", "n": 242 }, { "tag": "parkinsons disease", "n": 190 }, { "tag": "oxidative stress", "n": 172 }, { "tag": "MS", "n": 141 }, { "tag": "mouse model", "n": 138 }, { "tag": "cognitive decline", "n": 136 } ], "top_papers": [ { "paper_id": "arxiv:2005.02182", "title": "Opportunities for multiscale computational modelling of serotonergic drug effects in Alzheimer's disease", "citation_count": 21, "source": "arxiv" }, { "paper_id": "arxiv:1108.0132", "title": "Dual -1 Hahn polynomials:", "citation_count": 4, "source": "arxiv" }, { "paper_id": "arxiv:2308.08618", "title": "Modeling Biphasic, Non-Sigmoidal Dose-Response Relationships: Comparison of Brain-Cousens and Cedergreen Models for a Biochemical Dataset", "citation_count": 4, "source": "arxiv" }, { "paper_id": "arxiv:1801.01533", "title": "Computational Analysis for the Rational Design of Anti-Amyloid Beta (A\u03b2) Antibodies", "citation_count": 0, "source": "arxiv" }, { "paper_id": "biorxiv:10.1101/2025.05.31.657128", "title": "Oxidative stress mediates cardiac electrophysiological injury in inhalation exposure to flavored vaping products.", "citation_count": 0, "source": "biorxiv" } ] }, { "id": 25, "size": 5393, "top_tags": [ { "tag": "DNA", "n": 666 }, { "tag": "RNA", "n": 509 }, { "tag": "ATP", "n": 139 }, { "tag": "structural basis", "n": 137 }, { "tag": "ER", "n": 134 }, { "tag": "EM", "n": 130 }, { "tag": "biomolecular condensates", "n": 106 }, { "tag": "protein interactions", "n": 95 } ], "top_papers": [ { "paper_id": "arxiv:1412.2779", "title": "Persistent homology analysis of protein structure, flexibility, and folding", "citation_count": 248, "source": "arxiv" }, { "paper_id": "arxiv:1505.01138", "title": "Modeling of protein\u2013peptide interactions using the CABS-dock web server for binding site search and flexible docking", "citation_count": 161, "source": "arxiv" }, { "paper_id": "arxiv:1607.03783", "title": "Statistical Mechanics of Ligand\u2013Receptor Noncovalent Association, Revisited: Binding Site and Standard State Volumes in Modern Alchemical Theories", "citation_count": 57, "source": "arxiv" }, { "paper_id": "arxiv:1802.05669", "title": "Minimum Energy Paths and Transition States by Curve Optimization", "citation_count": 47, "source": "arxiv" }, { "paper_id": "arxiv:1905.05942", "title": "Protein-Folding Analysis Using Features Obtained by Persistent Homology", "citation_count": 30, "source": "arxiv" } ] }, { "id": 36, "size": 5131, "top_tags": [ { "tag": "MIMO", "n": 331 }, { "tag": "wireless networks", "n": 328 }, { "tag": "cognitive radio", "n": 214 }, { "tag": "SNR", "n": 213 }, { "tag": "cognitive radio networks", "n": 196 }, { "tag": "secondary users", "n": 177 }, { "tag": "CSI", "n": 148 }, { "tag": "MAC", "n": 141 } ], "top_papers": [ { "paper_id": "arxiv:0906.5394", "title": "Wireless Network Information Flow: A Deterministic Approach", "citation_count": 854, "source": "arxiv" }, { "paper_id": "arxiv:1003.5309", "title": "Gossip Algorithms for Distributed Signal Processing", "citation_count": 724, "source": "arxiv" }, { "paper_id": "arxiv:0704.2475", "title": "Physical Layer Network Coding", "citation_count": 703, "source": "arxiv" }, { "paper_id": "arxiv:1305.0817", "title": "Optimal Relay Selection for Physical-Layer Security in Cooperative Wireless Networks", "citation_count": 510, "source": "arxiv" }, { "paper_id": "arxiv:0809.0016", "title": "An Overview of the Transmission Capacity of Wireless Networks", "citation_count": 435, "source": "arxiv" } ] }, { "id": 39, "size": 5112, "top_tags": [ { "tag": "dynamical systems", "n": 212 }, { "tag": "kuramoto model", "n": 201 }, { "tag": "phase oscillators", "n": 191 }, { "tag": "chimera states", "n": 161 }, { "tag": "numerical simulations", "n": 148 }, { "tag": "complex networks", "n": 142 }, { "tag": "cellular automata", "n": 142 }, { "tag": "pattern formation", "n": 125 } ], "top_papers": [ { "paper_id": "arxiv:1208.0045", "title": "Synchronization in complex oscillator networks and smart grids", "citation_count": 883, "source": "arxiv" }, { "paper_id": "arxiv:1403.6204", "title": "Chimera states: coexistence of coherence and incoherence in networks of coupled oscillators", "citation_count": 787, "source": "arxiv" }, { "paper_id": "arxiv:1301.7608", "title": "Chimera states in mechanical oscillator networks", "citation_count": 639, "source": "arxiv" }, { "paper_id": "arxiv:0806.0594", "title": "Solvable Model for Chimera States of Coupled Oscillators", "citation_count": 622, "source": "arxiv" }, { "paper_id": "arxiv:0902.2773", "title": "Long time evolution of phase oscillator systems", "citation_count": 451, "source": "arxiv" } ] }, { "id": 20, "size": 5064, "top_tags": [ { "tag": "physical systems", "n": 198 }, { "tag": "formal verification", "n": 165 }, { "tag": "model checking", "n": 152 }, { "tag": "LTL", "n": 148 }, { "tag": "petri nets", "n": 120 }, { "tag": "formal methods", "n": 118 }, { "tag": "hybrid systems", "n": 111 }, { "tag": "linear temporal logic", "n": 102 } ], "top_papers": [ { "paper_id": "arxiv:2005.11401", "title": "Affordance-Compiled Intelligence: Observable-Only Cognitive Impedance Matching for No-Meta LLM-Integrated Systems", "citation_count": 2971, "source": "arxiv" }, { "paper_id": "arxiv:1505.05093", "title": "Programming With Models: Writing Statistical Algorithms for General Model Structures With NIMBLE", "citation_count": 997, "source": "arxiv" }, { "paper_id": "arxiv:1808.06255", "title": "Evolving Algebras 1993: Lipari Guide", "citation_count": 551, "source": "arxiv" }, { "paper_id": "arxiv:1708.06374", "title": "On a Formal Model of Safe and Scalable Self-driving Cars", "citation_count": 421, "source": "arxiv" }, { "paper_id": "arxiv:1807.00048", "title": "Formal Specification and Verification of Autonomous Robotic Systems", "citation_count": 264, "source": "arxiv" } ] }, { "id": 31, "size": 4849, "top_tags": [ { "tag": "DNA", "n": 217 }, { "tag": "RNA", "n": 170 }, { "tag": "pseudomonas aeruginosa", "n": 137 }, { "tag": "e. coli", "n": 107 }, { "tag": "staphylococcus aureus", "n": 102 }, { "tag": "antibiotic resistance", "n": 100 }, { "tag": "biofilm formation", "n": 98 }, { "tag": "antimicrobial resistance", "n": 96 } ], "top_papers": [ { "paper_id": "arxiv:1003.1266", "title": "Hitting and commute times in large graphs are often misleading", "citation_count": 9, "source": "arxiv" }, { "paper_id": "arxiv:2010.00624", "title": "Biocybersecurity -- A Converging Threat as an Auxiliary to War", "citation_count": 6, "source": "arxiv" }, { "paper_id": "arxiv:1312.2841", "title": "Predictive Comparative Qsar Analysis of as 5-Nitrofuran-2-Yl Derivatives Myco Bacterium Tuberculosis H37RV Inhibitors", "citation_count": 5, "source": "arxiv" }, { "paper_id": "arxiv:2004.03806", "title": "Proposing a fungal metabolite-Flaviolin as a potential inhibitor of 3CLpro of novel coronavirus SARS-CoV2 using docking and molecular dynamics", "citation_count": 5, "source": "arxiv" }, { "paper_id": "arxiv:2403.11911", "title": "Bacterial Communications and Computing in Internet of Everything (IoE)", "citation_count": 4, "source": "arxiv" } ] }, { "id": 6, "size": 4704, "top_tags": [ { "tag": "AI", "n": 1197 }, { "tag": "machine learning", "n": 628 }, { "tag": "artificial intelligence", "n": 499 }, { "tag": "XAI", "n": 407 }, { "tag": "explainable ai", "n": 361 }, { "tag": "ML", "n": 299 }, { "tag": "explainable artificial intelligence", "n": 280 }, { "tag": "machine learning models", "n": 278 } ], "top_papers": [ { "paper_id": "arxiv:1705.07874", "title": "A Unified Approach to Interpreting Model Predictions", "citation_count": 7622, "source": "arxiv" }, { "paper_id": "arxiv:1702.08608", "title": "Towards A Rigorous Science of Interpretable Machine Learning", "citation_count": 3133, "source": "arxiv" }, { "paper_id": "arxiv:1806.01261", "title": "Relational inductive biases, deep learning, and graph networks", "citation_count": 2401, "source": "arxiv" }, { "paper_id": "arxiv:2108.07258", "title": "On the Opportunities and Risks of Foundation Models", "citation_count": 2171, "source": "arxiv" }, { "paper_id": "arxiv:1907.07374", "title": "A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI", "citation_count": 2133, "source": "arxiv" } ] }, { "id": 41, "size": 4685, "top_tags": [ { "tag": "recommender systems", "n": 1244 }, { "tag": "collaborative filtering", "n": 436 }, { "tag": "recommendation systems", "n": 310 }, { "tag": "recommender system", "n": 265 }, { "tag": "language models", "n": 216 }, { "tag": "user preferences", "n": 216 }, { "tag": "sequential recommendation", "n": 185 }, { "tag": "CF", "n": 151 } ], "top_papers": [ { "paper_id": "arxiv:1301.7363", "title": "Empirical Analysis of Predictive Algorithms for Collaborative Filtering", "citation_count": 4515, "source": "arxiv" }, { "paper_id": "arxiv:1205.2618", "title": "BPR: Bayesian Personalized Ranking from Implicit Feedback", "citation_count": 4366, "source": "arxiv" }, { "paper_id": "arxiv:1905.08108", "title": "Neural Graph Collaborative Filtering", "citation_count": 2988, "source": "arxiv" }, { "paper_id": "arxiv:1905.07854", "title": "KGAT", "citation_count": 2050, "source": "arxiv" }, { "paper_id": "arxiv:1606.00931", "title": "DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network", "citation_count": 1876, "source": "arxiv" } ] }, { "id": 46, "size": 4461, "top_tags": [ { "tag": "ECM", "n": 163 }, { "tag": "extracellular matrix", "n": 119 }, { "tag": "extracellular vesicles", "n": 94 }, { "tag": "DNA", "n": 89 }, { "tag": "mechanical properties", "n": 62 }, { "tag": "EV", "n": 59 }, { "tag": "MRI", "n": 59 }, { "tag": "+ /-", "n": 59 } ], "top_papers": [ { "paper_id": "arxiv:1204.0615", "title": "Stripe Formation in Bacterial Systems with Density-Suppressed Motility", "citation_count": 194, "source": "arxiv" }, { "paper_id": "arxiv:2101.00442", "title": "CryoNuSeg: A dataset for nuclei instance segmentation of cryosectioned H&E-stained histological images", "citation_count": 110, "source": "arxiv" }, { "paper_id": "arxiv:1803.00046", "title": "Continuum contact models for coupled adhesion and friction", "citation_count": 89, "source": "arxiv" }, { "paper_id": "arxiv:1210.3655", "title": "Reliable transport through a microfabricatedX-junction surface-electrode ion trap", "citation_count": 82, "source": "arxiv" }, { "paper_id": "arxiv:1204.4147", "title": "Controlling trapping potentials and stray electric fields in a microfabricated ion trap through design and compensation", "citation_count": 80, "source": "arxiv" } ] }, { "id": 60, "size": 4404, "top_tags": [ { "tag": "differential privacy", "n": 1025 }, { "tag": "DP", "n": 508 }, { "tag": "machine learning", "n": 339 }, { "tag": "sensitive information", "n": 274 }, { "tag": "sensitive data", "n": 213 }, { "tag": "privacy concerns", "n": 192 }, { "tag": "data privacy", "n": 187 }, { "tag": "private data", "n": 179 } ], "top_papers": [ { "paper_id": "arxiv:1607.00133", "title": "Deep Learning with Differential Privacy", "citation_count": 5790, "source": "arxiv" }, { "paper_id": "arxiv:1407.6981", "title": "RAPPOR", "citation_count": 1494, "source": "arxiv" }, { "paper_id": "arxiv:0903.3276", "title": "De-anonymizing Social Networks", "citation_count": 1318, "source": "arxiv" }, { "paper_id": "arxiv:1702.07476", "title": "R\u00e9nyi Differential Privacy", "citation_count": 1056, "source": "arxiv" }, { "paper_id": "arxiv:1710.06963", "title": "Learning Differentially Private Recurrent Language Models", "citation_count": 671, "source": "arxiv" } ] }, { "id": 45, "size": 4104, "top_tags": [ { "tag": "reinforcement learning", "n": 376 }, { "tag": "AI", "n": 364 }, { "tag": "MARL", "n": 259 }, { "tag": "RL", "n": 206 }, { "tag": "artificial intelligence", "n": 171 }, { "tag": "multi - agent systems", "n": 158 }, { "tag": "deep reinforcement learning", "n": 125 }, { "tag": "machine learning", "n": 115 } ], "top_papers": [ { "paper_id": "arxiv:1105.5449", "title": "AntNet: Distributed Stigmergetic Control for Communications Networks", "citation_count": 1581, "source": "arxiv" }, { "paper_id": "arxiv:1606.06565", "title": "Agnostic Learning with Unknown Utilities", "citation_count": 1397, "source": "arxiv" }, { "paper_id": "arxiv:1712.01815", "title": "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm", "citation_count": 1080, "source": "arxiv" }, { "paper_id": "arxiv:1912.06680", "title": "Dota 2 with Large Scale Deep Reinforcement Learning", "citation_count": 1045, "source": "arxiv" }, { "paper_id": "arxiv:1706.02275", "title": "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments", "citation_count": 1015, "source": "arxiv" } ] }, { "id": 53, "size": 4048, "top_tags": [ { "tag": "DNA", "n": 252 }, { "tag": "genetic diversity", "n": 171 }, { "tag": "climate change", "n": 124 }, { "tag": "genetic variation", "n": 101 }, { "tag": "genetic basis", "n": 93 }, { "tag": "RNA", "n": 88 }, { "tag": "gene expression", "n": 80 }, { "tag": "gene flow", "n": 71 } ], "top_papers": [ { "paper_id": "arxiv:1401.5201", "title": "Hyperspectral imaging spectroscopy of a Mars analogue environment at the North Pole Dome, Pilbara Craton, Western Australia", "citation_count": 78, "source": "arxiv" }, { "paper_id": "arxiv:1505.05815", "title": "Inference of Ancestral Recombination Graphs through Topological Data Analysis", "citation_count": 75, "source": "arxiv" }, { "paper_id": "arxiv:1405.6623", "title": "The Dawn of Open Access to Phylogenetic Data", "citation_count": 65, "source": "arxiv" }, { "paper_id": "arxiv:1707.00062", "title": "The SpeX Prism Library Analysis Toolkit (SPLAT): A Data Curation Model", "citation_count": 27, "source": "arxiv" }, { "paper_id": "arxiv:1512.02484", "title": "Uranium distribution in the Variscan Basement of Northeastern Sardinia", "citation_count": 17, "source": "arxiv" } ] }, { "id": 38, "size": 4005, "top_tags": [ { "tag": "language models", "n": 676 }, { "tag": "dialogue systems", "n": 389 }, { "tag": "LLMs", "n": 292 }, { "tag": "AI", "n": 280 }, { "tag": "LLM", "n": 216 }, { "tag": "conversational agents", "n": 163 }, { "tag": "language model", "n": 144 }, { "tag": "dialog systems", "n": 138 } ], "top_papers": [ { "paper_id": "arxiv:2307.09288", "title": "Llama 2: Open Foundation and Fine-Tuned Chat Models", "citation_count": 2614, "source": "arxiv" }, { "paper_id": "arxiv:1506.05869", "title": "A Neural Conversational Model", "citation_count": 1504, "source": "arxiv" }, { "paper_id": "arxiv:2405.18346", "title": "Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation", "citation_count": 1017, "source": "arxiv" }, { "paper_id": "arxiv:1502.05698", "title": "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks", "citation_count": 720, "source": "arxiv" }, { "paper_id": "arxiv:2201.08239", "title": "LaMDA: Language Models for Dialog Applications", "citation_count": 705, "source": "arxiv" } ] }, { "id": 24, "size": 3985, "top_tags": [ { "tag": "federated learning", "n": 2386 }, { "tag": "FL", "n": 1773 }, { "tag": "global model", "n": 458 }, { "tag": "machine learning", "n": 412 }, { "tag": "data privacy", "n": 343 }, { "tag": "data heterogeneity", "n": 222 }, { "tag": "central server", "n": 209 }, { "tag": "IID", "n": 205 } ], "top_papers": [ { "paper_id": "arxiv:1602.05629", "title": "Communication-Efficient Learning of Deep Networks from Decentralized\\n Data", "citation_count": 5177, "source": "arxiv" }, { "paper_id": "arxiv:1912.04977", "title": "Advances and Open Problems in Federated Learning", "citation_count": 4607, "source": "arxiv" }, { "paper_id": "arxiv:1908.07873", "title": "Federated Learning: Challenges, Methods, and Future Directions", "citation_count": 4560, "source": "arxiv" }, { "paper_id": "arxiv:2003.08119", "title": "The future of digital health with federated learning", "citation_count": 2445, "source": "arxiv" }, { "paper_id": "arxiv:1806.00582", "title": "Federated Learning with Non-IID Data", "citation_count": 1907, "source": "arxiv" } ] }, { "id": 5, "size": 3985, "top_tags": [ { "tag": "evolutionary algorithms", "n": 297 }, { "tag": "genetic algorithm", "n": 179 }, { "tag": "machine learning", "n": 179 }, { "tag": "optimization problems", "n": 141 }, { "tag": "bayesian optimization", "n": 137 }, { "tag": "genetic algorithms", "n": 134 }, { "tag": "search space", "n": 124 }, { "tag": "evolutionary algorithm", "n": 123 } ], "top_papers": [ { "paper_id": "arxiv:1008.3601", "title": "Crystal structure prediction via particle-swarm optimization", "citation_count": 2699, "source": "arxiv" }, { "paper_id": "arxiv:2002.04504", "title": "Pymoo: Multi-Objective Optimization in Python", "citation_count": 2084, "source": "arxiv" }, { "paper_id": "arxiv:1106.0675", "title": "The FF Planning System: Fast Plan Generation Through Heuristic Search", "citation_count": 1850, "source": "arxiv" }, { "paper_id": "arxiv:1211.6663", "title": "Bat algorithm: a novel approach for global engineering optimization", "citation_count": 1720, "source": "arxiv" }, { "paper_id": "arxiv:1804.03515", "title": "Hyperparameters and tuning strategies for random forest", "citation_count": 1452, "source": "arxiv" } ] }, { "id": 54, "size": 3939, "top_tags": [ { "tag": "math xmlns", "n": 128 }, { "tag": "standard model", "n": 119 }, { "tag": "MathML", "n": 75 }, { "tag": "dark matter", "n": 66 }, { "tag": "quantum field theory", "n": 48 }, { "tag": "LHC", "n": 48 }, { "tag": "QCD", "n": 47 }, { "tag": "persistent homology", "n": 43 } ], "top_papers": [ { "paper_id": "arxiv:2006.10256", "title": "Array programming with NumPy", "citation_count": 21771, "source": "arxiv" }, { "paper_id": "arxiv:1106.0522", "title": "MadGraph 5: going beyond", "citation_count": 2522, "source": "arxiv" }, { "paper_id": "arxiv:1503.06237", "title": "Holographic quantum error-correcting codes: toy models for the bulk/boundary correspondence", "citation_count": 815, "source": "arxiv" }, { "paper_id": "arxiv:1706.09436", "title": "Reevaluation of the hadronic vacuum polarisation contributions to the Standard Model predictions of the muon $$g-2$$ g - 2 and $${\\alpha (m_Z^2)}$$ \u03b1 ( m Z 2 ) using newest hadronic cross-section data", "citation_count": 624, "source": "arxiv" }, { "paper_id": "arxiv:1911.00003", "title": "Simulating lattice gauge theories within quantum technologies", "citation_count": 473, "source": "arxiv" } ] }, { "id": 16, "size": 3891, "top_tags": [ { "tag": "GWAS", "n": 380 }, { "tag": "DNA", "n": 335 }, { "tag": "association studies", "n": 244 }, { "tag": "RNA", "n": 163 }, { "tag": "genetic variants", "n": 160 }, { "tag": "PRS", "n": 145 }, { "tag": "CI", "n": 131 }, { "tag": "% ci", "n": 121 } ], "top_papers": [ { "paper_id": "arxiv:1509.02816", "title": "Bipartite Community Structure of eQTLs", "citation_count": 76, "source": "arxiv" }, { "paper_id": "arxiv:1407.3682", "title": "When Data Sharing Gets Close to 100%: What Human Paleogenetics Can Teach the Open Science Movement", "citation_count": 66, "source": "arxiv" }, { "paper_id": "arxiv:1707.01623", "title": "RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning", "citation_count": 32, "source": "arxiv" }, { "paper_id": "arxiv:1903.07847", "title": "Identify Statistical Similarities and Differences Between the Deadliest Cancer Types Through Gene Expression", "citation_count": 27, "source": "arxiv" }, { "paper_id": "arxiv:1703.02577", "title": "SAFETY: Secure gwAs in Federated Environment Through a hYbrid solution with Intel SGX and Homomorphic Encryption", "citation_count": 22, "source": "arxiv" } ] }, { "id": 63, "size": 3557, "top_tags": [ { "tag": "CI", "n": 329 }, { "tag": "% ci", "n": 309 }, { "tag": "SARS", "n": 286 }, { "tag": "CoV-2", "n": 273 }, { "tag": "HIV", "n": 248 }, { "tag": "TB", "n": 133 }, { "tag": "covid-19 pandemic", "n": 122 }, { "tag": "PCR", "n": 111 } ], "top_papers": [ { "paper_id": "arxiv:2003.11511", "title": "Contact Tracing Mobile Apps for COVID-19: Privacy Considerations and Related Trade-offs", "citation_count": 380, "source": "arxiv" }, { "paper_id": "arxiv:2005.10548", "title": "Coswara \u2014 A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis", "citation_count": 338, "source": "arxiv" }, { "paper_id": "arxiv:2002.05534", "title": "Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner", "citation_count": 197, "source": "arxiv" }, { "paper_id": "arxiv:2105.07844", "title": "Does \u201cAI\u201d stand for augmenting inequality in the era of covid-19 healthcare?", "citation_count": 167, "source": "arxiv" }, { "paper_id": "arxiv:2007.00621", "title": "In silico investigation of phytoconstituents from Indian medicinal herb \u2018Tinospora cordifolia(giloy)\u2019 against SARS-CoV-2 (COVID-19) by molecular dynamics approach", "citation_count": 156, "source": "arxiv" } ] }, { "id": 61, "size": 3483, "top_tags": [ { "tag": "DNA", "n": 281 }, { "tag": "microbial communities", "n": 223 }, { "tag": "RNA", "n": 142 }, { "tag": "gut microbiome", "n": 128 }, { "tag": "antimicrobial resistance", "n": 117 }, { "tag": "AMR", "n": 114 }, { "tag": "gut microbiota", "n": 79 }, { "tag": "microbial diversity", "n": 67 } ], "top_papers": [ { "paper_id": "arxiv:1205.0192", "title": "Large-scale compression of genomic sequence databases with the Burrows\u2013Wheeler transform", "citation_count": 144, "source": "arxiv" }, { "paper_id": "arxiv:1406.0426", "title": "Fast construction of FM-index for long sequence reads", "citation_count": 95, "source": "arxiv" }, { "paper_id": "arxiv:0901.3215", "title": "Multiseed Lossless Filtration", "citation_count": 71, "source": "arxiv" }, { "paper_id": "arxiv:1403.7481", "title": "Indexes of Large Genome Collections on a PC", "citation_count": 44, "source": "arxiv" }, { "paper_id": "arxiv:1902.02776", "title": "Modeling microbial abundances and dysbiosis with beta-binomial regression", "citation_count": 36, "source": "arxiv" } ] }, { "id": 42, "size": 3442, "top_tags": [ { "tag": "climate change", "n": 167 }, { "tag": "drosophila melanogaster", "n": 64 }, { "tag": "body size", "n": 59 }, { "tag": "DNA", "n": 54 }, { "tag": "population dynamics", "n": 53 }, { "tag": "environmental change", "n": 46 }, { "tag": "environmental conditions", "n": 46 }, { "tag": "species richness", "n": 34 } ], "top_papers": [ { "paper_id": "arxiv:1307.5631", "title": "Collective Behaviour without Collective Order in Wild Swarms of Midges", "citation_count": 267, "source": "arxiv" }, { "paper_id": "arxiv:1505.07071", "title": "The climatological relationships between wind and solar energy supply in Britain", "citation_count": 266, "source": "arxiv" }, { "paper_id": "arxiv:1605.03626", "title": "Predictability and hierarchy in Drosophila behavior", "citation_count": 234, "source": "arxiv" }, { "paper_id": "arxiv:1407.2414", "title": "Role of projection in the control of bird flocks", "citation_count": 190, "source": "arxiv" }, { "paper_id": "arxiv:1603.00869", "title": "Proto-cooperation: group hunting sailfish improve hunting success by alternating attacks on grouping prey", "citation_count": 103, "source": "arxiv" } ] } ]