{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2003.03675","title":"Dynamic Backdoor Attacks Against Machine Learning Models","created":"2020-03-07","cited_by_count":151},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"1803.09353","title":"Stochastic bandits robust to adversarial corruptions","created":"2018-03-25","cited_by_count":119},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2003.12613","title":"Adaptive Reward-Poisoning Attacks against Reinforcement Learning","created":"2020-03-27","cited_by_count":86},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84},{"id":"1608.08182","title":"Data Poisoning Attacks on Factorization-Based Collaborative Filtering","created":"2016-08-29","cited_by_count":83},{"id":"2003.12909","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","created":"2020-03-28","cited_by_count":81},{"id":"1911.08689","title":"Corruption-robust exploration in episodic reinforcement learning","created":"2019-11-20","cited_by_count":72},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2005.07099","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":63},{"id":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53},{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45},{"id":"2009.00774","title":"Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics","created":"2020-09-02","cited_by_count":38},{"id":"2106.02978","title":"Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks","created":"2021-06-05","cited_by_count":33},{"id":"1910.01907","title":"Attacking Vision-based Perception in End-to-End Autonomous Driving Models","created":"2019-10-02","cited_by_count":31},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31},{"id":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24},{"id":"2208.13663","title":"Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning","created":"2022-08-29","cited_by_count":21},{"id":"2402.02160","title":"Data Poisoning for In-context Learning","created":"2024-02-03","cited_by_count":21},{"id":"2102.06875","title":"Improved Corruption Robust Algorithms for Episodic Reinforcement Learning","created":"2021-02-13","cited_by_count":20},{"id":"2206.01888","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning","created":"2022-06-04","cited_by_count":20},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14},{"id":"2404.18191","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","created":"2024-04-28","cited_by_count":14},{"id":"1905.12282","title":"CopyCAT: Taking Control of Neural Policies with Constant Attacks","created":"2019-05-29","cited_by_count":12},{"id":"2303.03391","title":"Decision Transformer under Random Frame Dropping","created":"2023-03-03","cited_by_count":10},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10},{"id":"1910.05625","title":"What You See May Not Be What You Get: UCB Bandit Algorithms Robust to {\\epsilon}-Contamination","created":"2019-10-12","cited_by_count":6},{"id":"2505.15143","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","created":"2025-05-21","cited_by_count":5},{"id":"2506.01876","title":"In-Context Learning for Pure Exploration","created":"2025-06-02","cited_by_count":5},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4},{"id":"2410.19705","title":"Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks","created":"2024-10-25","cited_by_count":2}],"next_cursor":null}