{"total":193,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396,"area":null},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702,"area":"wm"},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265,"area":null},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2104.00405","title":"Avalanche: an End-to-End Library for Continual Learning","created":"2021-04-01","cited_by_count":124,"area":null},{"id":"2206.05229","title":"Measuring the Carbon Intensity of AI in Cloud Instances","created":"2022-06-10","cited_by_count":111,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2405.09980","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","created":"2024-05-16","cited_by_count":54,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46,"area":"mllm"},{"id":"2302.08476","title":"Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning","created":"2023-02-16","cited_by_count":42,"area":null},{"id":"2112.01882","title":"Incremental Learning in Semantic Segmentation from Image Labels","created":"2021-12-03","cited_by_count":39,"area":null},{"id":"2206.03066","title":"Recent Advances for Quantum Neural Networks in Generative Learning","created":"2022-06-07","cited_by_count":39,"area":null},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"area":null},{"id":"2306.08323","title":"How to estimate carbon footprint when training deep learning models? A guide and review","created":"2023-06-14","cited_by_count":34,"area":null},{"id":"2104.13467","title":"An optical neural network using less than 1 photon per multiplication","created":"2021-04-27","cited_by_count":30,"area":null},{"id":"2203.05071","title":"On the influence of over-parameterization in manifold based surrogates and deep neural operators","created":"2022-03-09","cited_by_count":29,"area":null},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2404.15939","title":"Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunications","created":"2024-04-24","cited_by_count":26,"area":"rag"},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2106.01288","title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence","created":"2021-06-02","cited_by_count":21,"area":null},{"id":"2205.09646","title":"Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models","created":"2022-05-19","cited_by_count":21,"area":null},{"id":"2311.02265","title":"Not all layers are equally as important: Every Layer Counts BERT","created":"2023-11-03","cited_by_count":21,"area":null},{"id":"2108.09052","title":"SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning","created":"2021-08-20","cited_by_count":20,"area":null},{"id":"2302.03350","title":"To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods","created":"2023-02-07","cited_by_count":19,"area":"safety"},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15,"area":null},{"id":"2212.05153","title":"Algorithmic progress in computer vision","created":"2022-12-10","cited_by_count":14,"area":null},{"id":"2301.00519","title":"Holistic Network Virtualization and Pervasive Network Intelligence for 6G","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2107.02621","title":"Energy Consumption of Deep Generative Audio Models","created":"2021-07-06","cited_by_count":12,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2309.02065","title":"Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2201.01820","title":"A Hybrid Quantum-Classical Neural Network Architecture for Binary Classification","created":"2022-01-05","cited_by_count":11,"area":null},{"id":"2304.00897","title":"Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models","created":"2023-04-03","cited_by_count":9,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2303.03986","title":"Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation","created":"2023-03-05","cited_by_count":8,"area":null},{"id":"2305.01743","title":"Photonic Advantage of Optical Encoders","created":"2023-05-02","cited_by_count":8,"area":null},{"id":"2402.18609","title":"ICE-SEARCH: A Language Model-Driven Feature Selection Approach","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2409.12111","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","created":"2024-09-18","cited_by_count":8,"area":"distill"},{"id":"2102.06604","title":"Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2111.06223","title":"Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities","created":"2021-11-07","cited_by_count":7,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2304.05511","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2412.20875","title":"Attention Is All You Need For Mixture-of-Depths Routing","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2102.05836","title":"Online Deterministic Annealing for Classification and Clustering","created":"2021-02-11","cited_by_count":6,"area":null},{"id":"2202.10452","title":"A Classical-Quantum Convolutional Neural Network for Detecting Pneumonia from Chest Radiographs","created":"2022-02-19","cited_by_count":6,"area":null},{"id":"2205.05180","title":"Massively Digitized Power Grid: Opportunities and Challenges of Use-inspired AI","created":"2022-05-10","cited_by_count":6,"area":null},{"id":"2409.05395","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","created":"2024-09-09","cited_by_count":6,"area":"mllm"},{"id":"2207.07338","title":"Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2211.01950","title":"Unlocking the potential of two-point cells for energy-efficient and resilient training of deep nets","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2306.02307","title":"Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings","created":"2023-06-04","cited_by_count":5,"area":"inference"},{"id":"2404.15471","title":"Training all-mechanical neural networks for task learning through in situ backpropagation","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2405.15925","title":"MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion Segmentation","created":"2024-05-24","cited_by_count":5,"area":"ssm"},{"id":"2505.05086","title":"Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2207.10835","title":"Characterizing Coherent Integrated Photonic Neural Networks under Imperfections","created":"2022-07-22","cited_by_count":4,"area":null},{"id":"2301.09235","title":"Learning Reservoir Dynamics with Temporal Self-Modulation","created":"2023-01-23","cited_by_count":4,"area":null},{"id":"2409.03306","title":"Towards training digitally-tied analog blocks via hybrid gradient computation","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2409.05080","title":"From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems","created":"2024-09-08","cited_by_count":4,"area":null},{"id":"2410.21868","title":"Improving In-Context Learning with Small Language Model Ensembles","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2412.14790","title":"YOLOv11 Optimization for Efficient Resource Utilization","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2501.13165","title":"QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networks","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2506.04285","title":"Training-free AI for Earth Observation Change Detection using Physics Aware Neuromorphic Networks","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2603.08725","title":"Performance Analysis of Edge and In-Sensor AI Processors: A Comparative Review","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2205.12961","title":"Position: Tensor Networks are a Valuable Asset for Green AI","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2209.02826","title":"Annealing Optimization for Progressive Learning with Stochastic Approximation","created":"2022-09-06","cited_by_count":3,"area":null},{"id":"2306.08191","title":"Solving Large-scale Spatial Problems with Convolutional Neural Networks","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2312.04216","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2312.05361","title":"Emergence and Function of Abstract Representations in Self-Supervised Transformers","created":"2023-12-08","cited_by_count":3,"area":"wm"},{"id":"2312.12483","title":"SCoTTi: Save Computation at Training Time with an adaptive framework","created":"2023-12-19","cited_by_count":3,"area":null},{"id":"2403.07454","title":"Fast, accurate and lightweight sequential simulation-based inference using Gaussian locally linear mappings","created":"2024-03-12","cited_by_count":3,"area":null},{"id":"2404.14146","title":"Physics-based reward driven image analysis in microscopy","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2407.07818","title":"The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2407.17161","title":"Quantum Supervised Learning","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2505.11856","title":"Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing","created":"2025-05-17","cited_by_count":3,"area":"rag"},{"id":"2105.00053","title":"PositNN: Training Deep Neural Networks with Mixed Low-Precision Posit","created":"2021-04-30","cited_by_count":2,"area":null},{"id":"2209.09882","title":"Soft Action Priors: Towards Robust Policy Transfer","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2210.10048","title":"AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2212.10430","title":"Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2303.16154","title":"Guided Transfer Learning","created":"2023-03-26","cited_by_count":2,"area":null},{"id":"2310.01536","title":"Algebras of actions in an agent's representations of the world","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2310.04349","title":"Toward a Plug-and-Play Vision-Based Grasping Module for Robotics","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2310.09457","title":"UCM-Net: A Lightweight and Efficient Solution for Skin Lesion Segmentation using MLP and CNN","created":"2023-10-14","cited_by_count":2,"area":null},{"id":"2311.02205","title":"An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2404.12406","title":"Lowering PyTorch's Memory Consumption for Selective Differentiation","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2406.01345","title":"BMRS: Bayesian Model Reduction for Structured Pruning","created":"2024-06-03","cited_by_count":2,"area":null}],"next_cursor":"100"}