{"total":160,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073,"area":"moe"},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306,"area":"diffusion"},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2104.13386","title":"Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems","created":"2021-04-27","cited_by_count":128,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2202.11097","title":"Message passing all the way up","created":"2022-02-22","cited_by_count":47,"area":null},{"id":"2309.12252","title":"Parallelizing non-linear sequential models over the sequence length","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2305.14701","title":"Modeling rapid language learning by distilling Bayesian priors into artificial neural networks","created":"2023-05-24","cited_by_count":42,"area":null},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41,"area":null},{"id":"2407.19115","title":"Towards Scalable and Stable Parallelization of Nonlinear RNNs","created":"2024-07-26","cited_by_count":38,"area":null},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"area":null},{"id":"2208.12590","title":"Ab-initio quantum chemistry with neural-network wavefunctions","created":"2022-08-26","cited_by_count":29,"area":null},{"id":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2402.02887","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","created":"2024-02-05","cited_by_count":28,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2210.04243","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","created":"2022-10-09","cited_by_count":26,"area":null},{"id":"2401.04491","title":"SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learning","created":"2024-01-09","cited_by_count":25,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2104.00749","title":"Anytime Dense Prediction with Confidence Adaptivity","created":"2021-04-01","cited_by_count":18,"area":null},{"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":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2306.12230","title":"Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2505.03977","title":"Call for Action: towards the next generation of symbolic regression benchmark","created":"2025-05-06","cited_by_count":17,"area":null},{"id":"2312.04836","title":"Thermodynamic Computing System for AI Applications","created":"2023-12-08","cited_by_count":16,"area":null},{"id":"2410.11415","title":"KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI","created":"2024-10-15","cited_by_count":16,"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":"2211.14627","title":"Where to Pay Attention in Sparse Training for Feature Selection?","created":"2022-11-26","cited_by_count":15,"area":null},{"id":"2302.06584","title":"Thermodynamic AI and the fluctuation frontier","created":"2023-02-09","cited_by_count":15,"area":null},{"id":"2506.08332","title":"ORFS-agent: Tool-Using Agents for Chip Design Optimization","created":"2025-06-10","cited_by_count":14,"area":"agents"},{"id":"2103.01636","title":"Sparse Training Theory for Scalable and Efficient Agents","created":"2021-03-02","cited_by_count":13,"area":null},{"id":"2302.06548","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2403.08058","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","created":"2024-03-12","cited_by_count":13,"area":"inference"},{"id":"2407.03036","title":"SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2201.01863","title":"CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs","created":"2022-01-05","cited_by_count":11,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2204.02804","title":"Federated Self-supervised Speech Representations: Are We There Yet?","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2209.00692","title":"Making Intelligence: Ethical Values in IQ and ML Benchmarks","created":"2022-09-01","cited_by_count":10,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2212.07634","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","created":"2022-12-15","cited_by_count":9,"area":"distill"},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2501.10526","title":"Solving Sparse Finite Element Problems on Neuromorphic Hardware","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2510.23972","title":"An efficient probabilistic hardware architecture for diffusion-like models","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2303.07200","title":"Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks","created":"2023-03-10","cited_by_count":7,"area":null},{"id":"2506.05259","title":"Learning long range dependencies through time reversal symmetry breaking","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2101.09090","title":"A shallow neural model for relation prediction","created":"2021-01-22","cited_by_count":6,"area":null},{"id":"2409.15022","title":"A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence Processing","created":"2024-09-23","cited_by_count":6,"area":"ssm"},{"id":"2502.15122","title":"MONSTER: Monash Scalable Time Series Evaluation Repository","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2306.11550","title":"Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency","created":"2023-06-05","cited_by_count":5,"area":null},{"id":"2310.20444","title":"Analyzing the Impact of Companies on AI Research Based on Publications","created":"2023-10-31","cited_by_count":5,"area":null},{"id":"2505.20137","title":"ePC: Fast and Deep Predictive Coding in Digital Simulation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.06644","title":"Spark Transformer: Reactivating Sparsity in FFN and Attention","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2107.07741","title":"When does loss-based prioritization fail?","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2107.08148","title":"Declarative Machine Learning Systems","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2205.08377","title":"Should attention be all we need? The epistemic and ethical implications of unification in machine learning","created":"2022-05-09","cited_by_count":4,"area":null},{"id":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2310.07715","title":"To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2311.02394","title":"NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications","created":"2023-11-04","cited_by_count":4,"area":null},{"id":"2311.04386","title":"Harnessing Manycore Processors with Distributed Memory for Accelerated Training of Sparse and Recurrent Models","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2512.11843","title":"Spiking Manifesto","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2603.24654","title":"Spectral methods: crucial for machine learning, natural for quantum computers?","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2604.02334","title":"Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web","created":"2026-01-18","cited_by_count":4,"area":"agents"},{"id":"2110.10802","title":"A Data-Centric Optimization Framework for Machine Learning","created":"2021-10-20","cited_by_count":3,"area":null},{"id":"2206.07435","title":"Forecasting of depth and ego-motion with transformers and self-supervision","created":"2022-06-15","cited_by_count":3,"area":null},{"id":"2309.07181","title":"The Grand Illusion: The Myth of Software Portability and Implications for ML Progress","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2408.04583","title":"Unveiling the Power of Sparse Neural Networks for Feature Selection","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2409.12965","title":"Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2511.11581","title":"The Anatomy of a Triton Attention Kernel","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2601.22438","title":"Towards Resiliency in Large Language Model Serving with KevlarFlow","created":"2026-01-30","cited_by_count":3,"area":"inference"},{"id":"2602.01651","title":"On the Spatiotemporal Dynamics of Generalization in Neural Networks","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2106.05822","title":"GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2106.09686","title":"How Low Can We Go: Trading Memory for Error in Low-Precision Training","created":"2021-06-17","cited_by_count":2,"area":null},{"id":"2108.04217","title":"ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients","created":"2021-07-06","cited_by_count":2,"area":null}],"next_cursor":"100"}