{"total":372,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151,"area":"lr"},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2309.05837","title":"The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems","created":"2023-09-11","cited_by_count":88,"area":null},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59,"area":null},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2502.00935","title":"Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis","created":"2025-02-02","cited_by_count":45,"area":"wm"},{"id":"2108.01846","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","created":"2021-08-04","cited_by_count":39,"area":null},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2312.00812","title":"Empowering Autonomous Driving with Large Language Models: A Safety Perspective","created":"2023-11-28","cited_by_count":34,"area":"driving"},{"id":"2512.11891","title":"VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer","created":"2025-12-09","cited_by_count":34,"area":"vla"},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2410.10807","title":"HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees","created":"2024-10-14","cited_by_count":31,"area":null},{"id":"2105.10682","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","created":"2021-05-22","cited_by_count":30,"area":null},{"id":"2307.08336","title":"RAYEN: Imposition of Hard Convex Constraints on Neural Networks","created":"2023-07-17","cited_by_count":30,"area":null},{"id":"2212.03228","title":"ISAACS: Iterative Soft Adversarial Actor-Critic for Safety","created":"2022-12-06","cited_by_count":28,"area":null},{"id":"2306.13867","title":"Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems","created":"2023-06-24","cited_by_count":28,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2503.15707","title":"Safety Aware Task Planning via Large Language Models in Robotics","created":"2025-03-19","cited_by_count":24,"area":"lr"},{"id":"2509.20478","title":"Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations","created":"2025-09-24","cited_by_count":24,"area":"offlinerl"},{"id":"2105.08169","title":"Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perception","created":"2021-05-17","cited_by_count":23,"area":"driving"},{"id":"2210.05308","title":"Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees","created":"2022-10-11","cited_by_count":23,"area":null},{"id":"2110.01110","title":"Safe Control with Neural Network Dynamic Models","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2206.01463","title":"Safety Certification for Stochastic Systems via Neural Barrier Functions","created":"2022-06-03","cited_by_count":22,"area":null},{"id":"2405.01758","title":"CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning","created":"2024-05-02","cited_by_count":21,"area":"diffusion"},{"id":"2111.09971","title":"Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations","created":"2021-11-18","cited_by_count":20,"area":null},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2602.17560","title":"ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment","created":"2026-02-19","cited_by_count":19,"area":"alignment"},{"id":"2201.01918","title":"SABLAS: Learning Safe Control for Black-box Dynamical Systems","created":"2022-01-06","cited_by_count":17,"area":null},{"id":"2209.13308","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","created":"2022-09-27","cited_by_count":17,"area":null},{"id":"2410.11671","title":"Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents","created":"2024-10-15","cited_by_count":17,"area":"deeprl"},{"id":"2510.14959","title":"CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions","created":"2025-10-16","cited_by_count":17,"area":"deeprl"},{"id":"2405.00846","title":"Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination","created":"2024-05-01","cited_by_count":16,"area":null},{"id":"2405.14058","title":"Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates","created":"2024-05-22","cited_by_count":16,"area":"deeprl"},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"area":"deeprl"},{"id":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"id":"2101.05916","title":"Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability","created":"2021-01-15","cited_by_count":14,"area":null},{"id":"2101.06492","title":"Learning Robust Hybrid Control Barrier Functions for Uncertain Systems","created":"2021-01-16","cited_by_count":14,"area":null},{"id":"2310.09360","title":"Exact Verification of ReLU Neural Control Barrier Functions","created":"2023-10-13","cited_by_count":14,"area":null},{"id":"2503.10966","title":"Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping","created":"2025-03-14","cited_by_count":14,"area":"offlinerl"},{"id":"2106.07108","title":"Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertainty","created":"2021-06-13","cited_by_count":13,"area":null},{"id":"2110.07699","title":"Safe Autonomous Racing via Approximate Reachability on Ego-vision","created":"2021-10-14","cited_by_count":13,"area":null},{"id":"2203.13083","title":"Behavior Trees in Robot Control Systems","created":"2022-03-24","cited_by_count":13,"area":null},{"id":"2210.02300","title":"Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarios","created":"2022-10-05","cited_by_count":13,"area":"driving"},{"id":"2304.04066","title":"Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach","created":"2023-04-08","cited_by_count":13,"area":null},{"id":"2306.15512","title":"Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models","created":"2023-06-27","cited_by_count":13,"area":"diffusion"},{"id":"2410.16281","title":"Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2509.24243","title":"SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions","created":"2025-09-29","cited_by_count":12,"area":"diffusion"},{"id":"2104.08171","title":"Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2304.08743","title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2403.01410","title":"Barrier Functions Inspired Reward Shaping for Reinforcement Learning","created":"2024-03-03","cited_by_count":11,"area":"deeprl"},{"id":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2309.01267","title":"Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy","created":"2023-09-03","cited_by_count":10,"area":null},{"id":"2505.10547","title":"Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning","created":"2025-05-15","cited_by_count":10,"area":null},{"id":"2506.12544","title":"Constrained Diffusers for Safe Planning and Control","created":"2025-06-14","cited_by_count":10,"area":"diffusion"},{"id":"2201.01347","title":"Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments","created":"2022-01-04","cited_by_count":9,"area":null},{"id":"2307.03015","title":"Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance","created":"2023-07-06","cited_by_count":9,"area":null},{"id":"2310.08602","title":"Safe Deep Policy Adaptation","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2311.02227","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2408.15625","title":"CBF-LLM: Safe Control for LLM Alignment","created":"2024-08-28","cited_by_count":9,"area":"alignment"},{"id":"2412.09989","title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2511.18606","title":"How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints","created":"2025-11-23","cited_by_count":9,"area":null},{"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":"2604.16683","title":"Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning","created":"2026-04-17","cited_by_count":9,"area":"offlinerl"},{"id":"2209.10034","title":"Differentiable Safe Controller Design through Control Barrier Functions","created":"2022-09-20","cited_by_count":8,"area":null},{"id":"2210.09378","title":"Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation","created":"2022-10-17","cited_by_count":8,"area":null},{"id":"2308.12252","title":"How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy","created":"2023-08-23","cited_by_count":8,"area":null},{"id":"2404.16879","title":"Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2512.16705","title":"Olaf: Bringing an Animated Character to Life in the Physical World","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2105.12204","title":"Safe Value Functions","created":"2021-05-25","cited_by_count":7,"area":null},{"id":"2109.06689","title":"Reactive and Safe Road User Simulations using Neural Barrier Certificates","created":"2021-09-14","cited_by_count":7,"area":null},{"id":"2303.05694","title":"Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimization","created":"2023-03-10","cited_by_count":7,"area":null},{"id":"2405.00871","title":"Learning to Boost the Performance of Stable Nonlinear Systems","created":"2024-05-01","cited_by_count":7,"area":null},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2604.07644","title":"Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2208.02319","title":"Differentiable Predictive Control with Safety Guarantees: A Control Barrier Function Approach","created":"2022-08-03","cited_by_count":6,"area":null},{"id":"2304.06160","title":"Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNet","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2310.00887","title":"GRID: A Platform for General Robot Intelligence Development","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2411.15036","title":"Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium","created":"2024-11-22","cited_by_count":6,"area":null},{"id":"2205.05787","title":"Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models","created":"2022-05-11","cited_by_count":5,"area":null},{"id":"2207.04117","title":"Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents","created":"2022-07-08","cited_by_count":5,"area":null},{"id":"2309.11453","title":"Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2405.00316","title":"Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving","created":"2024-05-01","cited_by_count":5,"area":"driving"},{"id":"2412.04153","title":"A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks","created":"2024-12-05","cited_by_count":5,"area":"deeprl"},{"id":"2505.00908","title":"Learning Conservative Neural Control Barrier Functions from Offline Data","created":"2025-05-01","cited_by_count":5,"area":"offlinerl"},{"id":"2506.15693","title":"Verifiable Safety Q-Filters via Hamilton-Jacobi Reachability and Multiplicative Q-Networks","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.01728","title":"Constrained Decoding for Safe Robot Navigation Foundation Models","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2509.14758","title":"Designing Latent Safety Filters using Pre-Trained Vision Models","created":"2025-09-18","cited_by_count":5,"area":"wm"},{"id":"2511.06385","title":"From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies","created":"2025-11-09","cited_by_count":5,"area":"diffusion"},{"id":"2604.01723","title":"Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving","created":"2026-04-02","cited_by_count":5,"area":"vla"},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2605.22446","title":"Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts","created":"2026-05-21","cited_by_count":5,"area":"wm"},{"id":"2107.04247","title":"Structured Hammerstein-Wiener Model Learning for Model Predictive Control","created":"2021-07-09","cited_by_count":4,"area":null}],"next_cursor":"100"}