{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274},{"id":"2202.02435","title":"On Neural Differential Equations","created":"2022-02-04","cited_by_count":268},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1602.05179","title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","created":"2016-02-16","cited_by_count":259},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"2308.16369","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","created":"2023-08-31","cited_by_count":193},{"id":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2111.00254","title":"Equinox: neural networks in JAX via callable PyTrees and filtered transformations","created":"2021-10-30","cited_by_count":148},{"id":"1707.03663","title":"Underdamped Langevin MCMC: A non-asymptotic analysis","created":"2017-07-12","cited_by_count":133},{"id":"1605.07717","title":"Deep Structured Energy Based Models for Anomaly Detection","created":"2016-05-25","cited_by_count":114},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"1705.09048","title":"Convergence of Langevin MCMC in KL-divergence","created":"2017-05-25","cited_by_count":88},{"id":"2006.01981","title":"Training End-to-End Analog Neural Networks with Equilibrium Propagation","created":"2020-06-02","cited_by_count":63},{"id":"2003.01998","title":"Neural Enhanced Belief Propagation on Factor Graphs","created":"2020-03-04","cited_by_count":57},{"id":"1411.6156","title":"Efficiently learning Ising models on arbitrary graphs","created":"2014-11-22","cited_by_count":50},{"id":"2006.02080","title":"A mathematical model for automatic differentiation in machine learning","created":"2020-06-03","cited_by_count":45},{"id":"2206.09914","title":"A Langevin-like Sampler for Discrete Distributions","created":"2022-06-20","cited_by_count":44},{"id":"2402.01103","title":"Compositional Generative Modeling: A Single Model is Not All You Need","created":"2024-02-02","cited_by_count":41},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40},{"id":"2305.09880","title":"A survey of the Vision Transformers and their CNN-Transformer based Variants","created":"2023-05-17","cited_by_count":33},{"id":"2210.08572","title":"Automatic Differentiation of Programs with Discrete Randomness","created":"2022-10-16","cited_by_count":29},{"id":"2305.18321","title":"Training an Ising Machine with Equilibrium Propagation","created":"2023-05-22","cited_by_count":29},{"id":"2103.04992","title":"Self-learning Machines based on Hamiltonian Echo Backpropagation","created":"2021-03-08","cited_by_count":28},{"id":"2302.08933","title":"Universality laws for Gaussian mixtures in generalized linear models","created":"2023-02-17","cited_by_count":28},{"id":"1612.05024","title":"Optimal structure and parameter learning of Ising models","created":"2016-12-15","cited_by_count":26},{"id":"2110.02481","title":"Massively Parallel Probabilistic Computing with Sparse Ising Machines","created":"2021-10-06","cited_by_count":25},{"id":"2206.14897","title":"Discrete Langevin Sampler via Wasserstein Gradient Flow","created":"2022-06-29","cited_by_count":24},{"id":"2303.10728","title":"Training Deep Boltzmann Networks with Sparse Ising Machines","created":"2023-03-19","cited_by_count":24},{"id":"2210.04055","title":"AI and ML Accelerator Survey and Trends","created":"2022-10-08","cited_by_count":23},{"id":"2312.04836","title":"Thermodynamic Computing System for AI Applications","created":"2023-12-08","cited_by_count":16},{"id":"2302.06584","title":"Thermodynamic AI and the fluctuation frontier","created":"2023-02-09","cited_by_count":15},{"id":"2107.02308","title":"A visual introduction to Gaussian Belief Propagation","created":"2021-07-05","cited_by_count":13},{"id":"2302.06457","title":"A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms","created":"2023-02-13","cited_by_count":13},{"id":"1808.09111","title":"Unsupervised Learning of Syntactic Structure with Invertible Neural Projections","created":"2018-08-28","cited_by_count":11},{"id":"2212.08340","title":"Neural Enhanced Belief Propagation for Multiobject Tracking","created":"2022-12-16","cited_by_count":11},{"id":"2304.05949","title":"CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learning","created":"2023-04-12","cited_by_count":11},{"id":"2409.19315","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","created":"2024-09-28","cited_by_count":11},{"id":"2312.08748","title":"All-to-all reconfigurability with sparse and higher-order Ising machines","created":"2023-11-21","cited_by_count":10},{"id":"2405.08467","title":"Equilibrium Propagation: the Quantum and the Thermal Cases","created":"2024-05-14","cited_by_count":10},{"id":"2510.23972","title":"An efficient probabilistic hardware architecture for diffusion-like models","created":"2025-10-28","cited_by_count":8},{"id":"1910.05744","title":"Powering Hidden Markov Model by Neural Network based Generative Models","created":"2019-10-13","cited_by_count":7},{"id":"1911.12675","title":"Continuous Dropout","created":"2019-11-28","cited_by_count":7},{"id":"1610.00053","title":"Superconducting optoelectronic circuits for neuromorphic computing","created":"2016-09-30","cited_by_count":6},{"id":"2102.11038","title":"Introducing the Hidden Neural Markov Chain framework","created":"2021-02-17","cited_by_count":6},{"id":"2306.07961","title":"Differentiating Metropolis-Hastings to Optimize Intractable Densities","created":"2023-06-13","cited_by_count":6},{"id":"2105.12903","title":"Neural Enhanced Belief Propagation for Cooperative Localization","created":"2021-05-27","cited_by_count":5},{"id":"2311.17166","title":"Is stochastic thermodynamics the key to understanding the energy costs of computation?","created":"2023-11-28","cited_by_count":5},{"id":"2107.00730","title":"Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability","created":"2021-07-01","cited_by_count":4},{"id":"2203.11618","title":"Distributing Collaborative Multi-Robot Planning with Gaussian Belief Propagation","created":"2022-03-22","cited_by_count":4},{"id":"2503.01177","title":"Scalable Connectivity for Ising Machines: Dense to Sparse","created":"2025-03-03","cited_by_count":4},{"id":"2506.19136","title":"Local Learning Rules for Out-of-Equilibrium Physical Generative Models","created":"2025-06-23","cited_by_count":4},{"id":"2507.17886","title":"Neuromorphic Computing: A Theoretical Framework for Time, Space, and Energy Scaling","created":"2025-07-23","cited_by_count":4},{"id":"2509.15324","title":"Training thermodynamic computers by gradient descent","created":"2025-09-18","cited_by_count":4},{"id":"1510.00756","title":"Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width","created":"2015-10-02","cited_by_count":3},{"id":"1811.10581","title":"HOGWILD!-Gibbs can be PanAccurate","created":"2018-11-26","cited_by_count":3},{"id":"2008.04436","title":"Ising Model Optimization Problems on a FPGA Accelerated Restricted Boltzmann Machine","created":"2020-08-10","cited_by_count":3},{"id":"1901.09712","title":"Ising Models with Latent Conditional Gaussian Variables","created":"2019-01-28","cited_by_count":2},{"id":"2410.01793","title":"Thermodynamic Bayesian Inference","created":"2024-10-02","cited_by_count":2},{"id":"1603.07758","title":"A universal tradeoff between power, precision and speed in physical communication","created":"2016-03-24","cited_by_count":1},{"id":"2310.07516","title":"Energy Estimates Across Layers of Computing: From Devices to Large-Scale Applications in Machine Learning for Natural Language Processing, Scientific Computing, and Cryptocurrency Mining","created":"2023-10-11","cited_by_count":1},{"id":"2601.04358","title":"Energy-Time-Accuracy Tradeoffs in Thermodynamic Computing","created":"2026-01-07","cited_by_count":1}],"next_cursor":null}