{"list":"other","total":51,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"1509.01149","title":"Model Predictive Path Integral Control using Covariance Variable Importance Sampling","created":"2015-09-03","cited_by_count":124},{"id":"2205.13600","title":"MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control","created":"2022-05-26","cited_by_count":80},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80},{"id":"2204.00616","title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","created":"2022-04-01","cited_by_count":24},{"id":"2503.18871","title":"Bootstrapped Model Predictive Control","created":"2025-03-24","cited_by_count":16},{"id":"2605.08732","title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","created":"2026-05-09","cited_by_count":15},{"id":"2606.26217","title":"Fast LeWorldModel","created":"2026-06-24","cited_by_count":15},{"id":"2306.00867","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","created":"2023-06-01","cited_by_count":14},{"id":"2502.03550","title":"TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint","created":"2025-02-05","cited_by_count":14},{"id":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13},{"id":"2209.14887","title":"Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion","created":"2022-09-29","cited_by_count":12},{"id":"2605.01194","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","created":"2026-05-02","cited_by_count":9},{"id":"2606.27326","title":"Hallucination in World Models is Predictable and Preventable","created":"2026-06-25","cited_by_count":8},{"id":"1710.04731","title":"Planning, Fast and Slow: A Framework for Adaptive Real-Time Safe Trajectory Planning","created":"2017-10-12","cited_by_count":7},{"id":"2503.05238","title":"Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation","created":"2025-03-07","cited_by_count":6},{"id":"2607.17454","title":"Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation","created":"2026-07-20","cited_by_count":6},{"id":"2109.09889","title":"A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning","created":"2021-09-21","cited_by_count":5},{"id":"2604.02965","title":"Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA","created":"2026-04-03","cited_by_count":5},{"id":"2505.13549","title":"TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion","created":"2025-05-19","cited_by_count":3},{"id":"2510.14643","title":"Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation","created":"2025-10-16","cited_by_count":3},{"id":"2512.17250","title":"Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction","created":"2025-12-19","cited_by_count":3},{"id":"2606.06660","title":"AEGIS: A Backup Reflex for Physical AI","created":"2026-06-04","cited_by_count":3},{"id":"2606.23079","title":"AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control","created":"2026-06-22","cited_by_count":3},{"id":"2606.31132","title":"ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies","created":"2026-06-30","cited_by_count":3},{"id":"2608.24855","title":"LeFlow: Generative Latent Flow Planning for World Models","created":"2026-08-25","cited_by_count":3},{"id":"2605.16692","title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","created":"2026-05-15","cited_by_count":2},{"id":"2606.24039","title":"TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU","created":"2026-06-23","cited_by_count":2},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2},{"id":"2608.05084","title":"Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control","created":"2026-08-05","cited_by_count":2},{"id":"2608.07065","title":"AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies","created":"2026-08-07","cited_by_count":2},{"id":"1703.05088","title":"Event-Triggered Intermittent Sampling for Nonlinear Model Predictive Control","created":"2017-03-15","cited_by_count":1},{"id":"2410.12142","title":"Characterizing and Optimizing Real-Time Optimal Control for Embedded SoCs","created":"2024-10-16","cited_by_count":1},{"id":"2506.12095","title":"DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion","created":"2025-06-12","cited_by_count":1},{"id":"2601.16686","title":"Adaptive Reinforcement and Model Predictive Control Switching for Safe Human-Robot Cooperative Navigation","created":"2026-01-23","cited_by_count":1},{"id":"2605.04568","title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","created":"2026-05-06","cited_by_count":1},{"id":"2607.11964","title":"LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving","created":"2026-07-12","cited_by_count":1},{"id":"2607.12523","title":"OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning","created":"2026-07-14","cited_by_count":1},{"id":"2607.16421","title":"When to Plan: Learning to Select Between Reactive Control and Deliberative Planning","created":"2026-07-17","cited_by_count":1},{"id":"2609.01260","title":"Dual Process Motion Planning","created":"2026-09-01","cited_by_count":1}],"next_cursor":null}