{"list":"other","total":57,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2011.03277","title":"Modular Primitives for High-Performance Differentiable Rendering","created":"2020-11-06","cited_by_count":441},{"id":"1904.01786","title":"Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning","created":"2019-04-03","cited_by_count":420},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"1701.02434","title":"A Conceptual Introduction to Hamiltonian Monte Carlo","created":"2017-01-10","cited_by_count":209},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195},{"id":"1912.11554","title":"Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro","created":"2019-12-24","cited_by_count":191},{"id":"2002.04087","title":"Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy","created":"2020-02-10","cited_by_count":183},{"id":"1611.01989","title":"DeepCoder: Learning to Write Programs","created":"2016-11-07","cited_by_count":149},{"id":"1611.01652","title":"A Differentiable Physics Engine for Deep Learning in Robotics","created":"2016-11-05","cited_by_count":108},{"id":"1711.10604","title":"TensorFlow Distributions","created":"2017-11-28","cited_by_count":106},{"id":"1804.06557","title":"The Limits and Potentials of Deep Learning for Robotics","created":"2018-04-18","cited_by_count":104},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2405.21015","title":"The rising costs of training frontier AI models","created":"2024-05-31","cited_by_count":95},{"id":"1805.04276","title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","created":"2018-05-11","cited_by_count":84},{"id":"2409.09359","title":"Symbolic Regression with a Learned Concept Library","created":"2024-09-14","cited_by_count":83},{"id":"2011.04217","title":"NeuralSim: Augmenting Differentiable Simulators with Neural Networks","created":"2020-11-09","cited_by_count":82},{"id":"1801.04016","title":"Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution","created":"2018-01-11","cited_by_count":66},{"id":"2211.16605","title":"Top-Down Synthesis for Library Learning","created":"2022-11-29","cited_by_count":58},{"id":"1909.06586","title":"Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control","created":"2019-09-14","cited_by_count":54},{"id":"2011.01808","title":"Bayesian Workflow","created":"2020-11-03","cited_by_count":49},{"id":"2103.00946","title":"A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulation","created":"2021-03-01","cited_by_count":38},{"id":"2402.10797","title":"BlackJAX: Composable Bayesian inference in JAX","created":"2024-02-16","cited_by_count":26},{"id":"2405.17784","title":"Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation","created":"2024-05-28","cited_by_count":20},{"id":"1907.06249","title":"Bayesian Synthesis of Probabilistic Programs for Automatic Data Modeling","created":"2019-07-14","cited_by_count":19},{"id":"2006.16653","title":"Involutive MCMC: a Unifying Framework","created":"2020-06-30","cited_by_count":19},{"id":"2104.08188","title":"I Find Your Lack of Uncertainty in Computer Vision Disturbing","created":"2021-04-16","cited_by_count":16},{"id":"1904.11433","title":"A pressure field model for fast, robust approximation of net contact force and moment between nominally rigid objects","created":"2019-04-25","cited_by_count":8},{"id":"2312.04574","title":"Differentiable Visual Computing for Inverse Problems and Machine Learning","created":"2023-11-21","cited_by_count":7},{"id":"2010.09802","title":"A Differentiable Newton Euler Algorithm for Multi-body Model Learning","created":"2020-10-19","cited_by_count":6},{"id":"2306.02049","title":"LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas","created":"2023-06-03","cited_by_count":6},{"id":"2110.04157","title":"Velocity Level Approximation of Pressure Field Contact Patches","created":"2021-10-08","cited_by_count":5},{"id":"1807.00403","title":"Towards Mixed Optimization for Reinforcement Learning with Program Synthesis","created":"2018-07-01","cited_by_count":4},{"id":"2305.08373","title":"AcroMonk: A Minimalist Underactuated Brachiating Robot","created":"2023-05-15","cited_by_count":4},{"id":"2409.08351","title":"Bayesian Inverse Graphics for Few-Shot Concept Learning","created":"2024-09-12","cited_by_count":2}],"next_cursor":null}