{"list":"other","total":53,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"1802.03471","title":"Certified Robustness to Adversarial Examples with Differential Privacy","created":"2018-02-09","cited_by_count":468},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2002.08118","title":"Randomized Smoothing of All Shapes and Sizes","created":"2020-02-19","cited_by_count":147},{"id":"2101.06549","title":"AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles","created":"2021-01-16","cited_by_count":137},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"2510.16732","title":"A Comprehensive Survey on World Models for Embodied AI","created":"2025-10-19","cited_by_count":68},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67},{"id":"2501.11260","title":"A Survey of World Models for Autonomous Driving","created":"2025-01-20","cited_by_count":60},{"id":"1807.04644","title":"Algorithms that Remember: Model Inversion Attacks and Data Protection Law","created":"2018-07-12","cited_by_count":55},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"2501.10100","title":"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics","created":"2025-01-17","cited_by_count":51},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30},{"id":"2006.04363","title":"Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models","created":"2020-06-08","cited_by_count":28},{"id":"2206.10524","title":"Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control","created":"2022-06-21","cited_by_count":28},{"id":"2503.22759","title":"Data Poisoning in Deep Learning: A Survey","created":"2025-03-27","cited_by_count":20},{"id":"2301.07487","title":"Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness","created":"2023-01-17","cited_by_count":19},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19},{"id":"2601.03905","title":"Current Agents Fail to Leverage World Model as Tool for Foresight","created":"2026-01-07","cited_by_count":17},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12},{"id":"2503.02143","title":"Four Principles for Physically Interpretable World Models","created":"2025-03-04","cited_by_count":10},{"id":"2405.11982","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","created":"2024-05-20","cited_by_count":9},{"id":"2411.07690","title":"World Models: The Safety Perspective","created":"2024-11-12","cited_by_count":9},{"id":"2306.05873","title":"Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions","created":"2023-06-09","cited_by_count":7},{"id":"2406.16979","title":"Understanding and Diagnosing Deep Reinforcement Learning","created":"2024-06-23","cited_by_count":6},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4},{"id":"2410.01927","title":"Risk Alignment in Agentic AI Systems","created":"2024-10-02","cited_by_count":3},{"id":"2508.06096","title":"Bounding Distributional Shifts in World Modeling through Novelty Detection","created":"2025-08-08","cited_by_count":2},{"id":"2404.19291","title":"Dynamic Human Trust Modeling of Autonomous Agents With Varying Capability and Strategy","created":"2024-04-30","cited_by_count":1},{"id":"2503.23820","title":"When Counterfactual Reasoning Fails: Chaos and Real-World Complexity","created":"2025-03-31","cited_by_count":1},{"id":"2511.18721","title":"Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM","created":"2025-11-24","cited_by_count":1}],"next_cursor":null}