{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1406.2541","title":"Predictive Entropy Search for Efficient Global Optimization of Black-box Functions","created":"2014-06-10","cited_by_count":204},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106},{"id":"1907.07504","title":"Subspace Inference for Bayesian Deep Learning","created":"2019-07-17","cited_by_count":95},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89},{"id":"2010.14689","title":"Bayesian Deep Learning via Subnetwork Inference","created":"2020-10-28","cited_by_count":87},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73},{"id":"2006.14091","title":"Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences","created":"2020-06-24","cited_by_count":71},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69},{"id":"1910.04365","title":"Asking Easy Questions: A User-Friendly Approach to Active Reward Learning","created":"2019-10-10","cited_by_count":68},{"id":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32},{"id":"2407.20635","title":"Autonomous Improvement of Instruction Following Skills via Foundation Models","created":"2024-07-30","cited_by_count":32},{"id":"2107.05802","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","created":"2021-07-13","cited_by_count":28},{"id":"2402.10797","title":"BlackJAX: Composable Bayesian inference in JAX","created":"2024-02-16","cited_by_count":26},{"id":"1807.01969","title":"Variational Bayesian dropout: pitfalls and fixes","created":"2018-07-05","cited_by_count":22},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20},{"id":"2002.00941","title":"Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections","created":"2020-02-03","cited_by_count":19},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15},{"id":"2412.09477","title":"Bayesian Optimization via Continual Variational Last Layer Training","created":"2024-12-12","cited_by_count":13},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9},{"id":"2507.17013","title":"laplax -- Laplace Approximations with JAX","created":"2025-07-22","cited_by_count":5},{"id":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1}],"next_cursor":null}