{"total":107,"rows":[{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732,"area":null},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2108.02497","title":"How to avoid machine learning pitfalls: a guide for academic researchers","created":"2021-08-05","cited_by_count":35,"area":null},{"id":"2108.12627","title":"Generalized Huber Loss for Robust Learning and its Efficient Minimization for a Robust Statistics","created":"2021-08-28","cited_by_count":32,"area":null},{"id":"2403.02467","title":"Applied Causal Inference Powered by ML and AI","created":"2024-03-04","cited_by_count":30,"area":null},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2109.10294","title":"DeepSTL -- From English Requirements to Signal Temporal Logic","created":"2021-09-21","cited_by_count":22,"area":null},{"id":"2206.14373","title":"Theoretical Perspectives on Deep Learning Methods in Inverse Problems","created":"2022-06-29","cited_by_count":22,"area":null},{"id":"2309.03613","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","created":"2023-09-07","cited_by_count":20,"area":null},{"id":"2406.02611","title":"LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2201.02880","title":"Attention-based Random Forest and Contamination Model","created":"2022-01-08","cited_by_count":10,"area":null},{"id":"2412.17810","title":"Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction","created":"2024-12-23","cited_by_count":10,"area":null},{"id":"2508.03616","title":"Hidden Dynamics of Massive Activations in Transformer Training","created":"2025-08-05","cited_by_count":10,"area":null},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2301.05435","title":"Towards Single Camera Human 3D-Kinematics","created":"2023-01-13","cited_by_count":8,"area":null},{"id":"2310.04662","title":"HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2211.09024","title":"Phenomenological Causality","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2305.18357","title":"DeepSI: Interactive Deep Learning for Semantic Interaction","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2112.06071","title":"Multi-Attention Multiple Instance Learning","created":"2021-12-11","cited_by_count":6,"area":null},{"id":"2109.14797","title":"Emergency Vehicles Audio Detection and Localization in Autonomous Driving","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2207.05724","title":"AGBoost: Attention-based Modification of Gradient Boosting Machine","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2207.11842","title":"$\\textit{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications","created":"2022-07-24","cited_by_count":5,"area":null},{"id":"2210.13416","title":"A Continuous Convolutional Trainable Filter for Modelling Unstructured Data","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2305.11575","title":"The Deep Promotion Time Cure Model","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2206.04874","title":"The 1st Data Science for Pavements Challenge","created":"2022-06-10","cited_by_count":4,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2207.09139","title":"Heterogeneous Treatment Effect with Trained Kernels of the Nadaraya-Watson Regression","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2306.12045","title":"Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2309.08316","title":"How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2404.01492","title":"Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2509.01234","title":"RAMS: Residual-based adversarial-gradient moving sample method for scientific machine learning in solving partial differential equations","created":"2025-09-01","cited_by_count":4,"area":null},{"id":"2108.04855","title":"Attention-like feature explanation for tabular data","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2108.06446","title":"A fast asynchronous MCMC sampler for sparse Bayesian inference","created":"2021-08-14","cited_by_count":3,"area":null},{"id":"2110.13440","title":"A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures","created":"2021-10-26","cited_by_count":3,"area":null},{"id":"2303.18201","title":"TPMCF: Temporal QoS Prediction using Multi-Source Collaborative Features","created":"2023-03-30","cited_by_count":3,"area":null},{"id":"2106.13315","title":"Generalized Unsupervised Clustering of Hyperspectral Images of Geological Targets in the Near Infrared","created":"2021-06-24","cited_by_count":2,"area":null},{"id":"2112.03868","title":"EmTract: Extracting Emotions from Social Media","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2112.09727","title":"Rank4Class: A Ranking Formulation for Multiclass Classification","created":"2021-12-17","cited_by_count":2,"area":null},{"id":"2207.10858","title":"Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data","created":"2022-07-22","cited_by_count":2,"area":null},{"id":"2210.02558","title":"Improved Anomaly Detection by Using the Attention-Based Isolation Forest","created":"2022-10-05","cited_by_count":2,"area":null},{"id":"2210.17115","title":"ViT-LSLA: Vision Transformer with Light Self-Limited-Attention","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2304.14078","title":"ganX -- generate artificially new XRF a python library to generate MA-XRF raw data out of RGB images","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2307.05318","title":"Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2309.12204","title":"PrNet: A Neural Network for Correcting Pseudoranges to Improve Positioning with Android Raw GNSS Measurements","created":"2023-09-16","cited_by_count":2,"area":null},{"id":"2309.15869","title":"Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2403.14918","title":"Deep learning-based method for weather forecasting: A case study in Itoshima","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2410.05353","title":"Towards a Categorical Foundation of Deep Learning: A Survey","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2106.12178","title":"Combination of Convolutional Neural Network and Gated Recurrent Unit for Energy Aware Resource Allocation","created":"2021-06-23","cited_by_count":1,"area":null},{"id":"2109.08853","title":"A survey on deep learning approaches for breast cancer diagnosis","created":"2021-09-18","cited_by_count":1,"area":null},{"id":"2112.07019","title":"Synapse Compression for Event-Based Convolutional-Neural-Network Accelerators","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2203.06886","title":"DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection","created":"2022-03-14","cited_by_count":1,"area":null},{"id":"2205.00061","title":"The Directional Bias Helps Stochastic Gradient Descent to Generalize in Kernel Regression Models","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2206.15051","title":"Group-invariant tensor train networks for supervised learning","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2207.09499","title":"Deep Analysis of Visual Product Reviews","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2207.10805","title":"PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-model Transmission Systems","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2211.10793","title":"BENK: The Beran Estimator with Neural Kernels for Estimating the Heterogeneous Treatment Effect","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2309.12022","title":"Demystifying Visual Features of Movie Posters for Multi-Label Genre Identification","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2309.16825","title":"A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets","created":"2023-09-28","cited_by_count":1,"area":null},{"id":"2311.18149","title":"STF: Spatial Temporal Fusion for Trajectory Prediction","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2401.10685","title":"Towards End-to-End GPS Localization with Neural Pseudorange Correction","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2409.03805","title":"Exploratory Visual Analysis for Increasing Data Readiness in Artificial Intelligence Projects","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2504.14568","title":"Quantum-Enhanced Weight Optimization for Neural Networks Using Grover's Algorithm","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2508.10938","title":"Deep Learning for Automated Identification of Vietnamese Timber Species: A Tool for Ecological Monitoring and Conservation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2601.16880","title":"Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2601.19107","title":"TinyTorch: Building Machine Learning Systems from First Principles","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2202.07895","title":"Enhancing Causal Estimation through Unlabeled Offline Data","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2202.09446","title":"Learning Representations Robust to Group Shifts and Adversarial Examples","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2203.16161","title":"Recommendation of Compatible Outfits Conditioned on Style","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2205.00663","title":"An Application to Generate Style Guided Compatible Outfit","created":"2022-05-02","cited_by_count":0,"area":null},{"id":"2205.01226","title":"Adversarial attacks on an optical neural network","created":"2022-04-29","cited_by_count":0,"area":null},{"id":"2208.02808","title":"Leveraging the HW/SW Optimizations and Ecosystems that Drive the AI Revolution","created":"2022-08-04","cited_by_count":0,"area":null},{"id":"2209.09649","title":"Predicting Mutual Funds' Performance using Deep Learning and Ensemble Techniques","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2210.05168","title":"LARF: Two-level Attention-based Random Forests with a Mixture of Contamination Models","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2212.04875","title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","created":"2022-12-09","cited_by_count":0,"area":null},{"id":"2301.11707","title":"Improving deep learning precipitation nowcasting by using prior knowledge","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2304.05980","title":"Neural Attention Forests: Transformer-Based Forest Improvement","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2307.02975","title":"Transfer Learning for the Efficient Detection of COVID-19 from Smartphone Audio Data","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2308.07424","title":"Addressing Distribution Shift in RTB Markets via Exponential Tilting","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2309.09443","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2311.08141","title":"GMTR: Graph Matching Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2311.11974","title":"Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2312.00184","title":"Galaxy Classification: A machine learning approach for classifying shapes using numerical data","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2312.16805","title":"DarkShot: Lighting Dark Images with Low-Compute and High-Quality","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2401.05431","title":"TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.05432","title":"TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2403.13663","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2406.06538","title":"Understanding attention-based encoder-decoder networks: a case study with chess scoresheet recognition","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2406.12262","title":"Investigating Data Usage for Inductive Conformal Predictors","created":"2024-06-18","cited_by_count":0,"area":null},{"id":"2408.17101","title":"Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.03554","title":"Artificial intelligence inspired freeform optics design: a review","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.11162","title":"Towards General Deepfake Detection with Dynamic Curriculum","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.13409","title":"Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2410.16302","title":"Computational design of target-specific linear peptide binders with TransformerBeta","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2410.19764","title":"Unraveling Movie Genres through Cross-Attention Fusion of Bi-Modal Synergy of Poster","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2411.14665","title":"Double Machine Learning for Adaptive Causal Representation in High-Dimensional Data","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2504.03799","title":"Experimental Study on Time Series Analysis of Lower Limb Rehabilitation Exercise Data Driven by Novel Model Architecture and Large Models","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2506.10407","title":"Semi-Tensor-Product Based Convolutional Neural Networks","created":"2025-06-12","cited_by_count":0,"area":null}],"next_cursor":"100"}