{"list":"other","total":60,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80},{"id":"1802.05313","title":"Reinforcement Learning from Imperfect Demonstrations","created":"2018-02-14","cited_by_count":75},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56},{"id":"2502.02588","title":"Calibrated Multi-Preference Optimization for Aligning Diffusion Models","created":"2025-02-04","cited_by_count":41},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28},{"id":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27},{"id":"2501.12735","title":"Online Preference Alignment for Language Models via Count-based Exploration","created":"2025-01-22","cited_by_count":26},{"id":"2412.05469","title":"Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization","created":"2024-12-06","cited_by_count":20},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16},{"id":"1906.03979","title":"Optimal Exploitation of Clustering and History Information in Multi-Armed Bandit","created":"2019-05-31","cited_by_count":14},{"id":"2308.12050","title":"Aligning Language Models with Offline Learning from Human Feedback","created":"2023-08-23","cited_by_count":14},{"id":"2210.00025","title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","created":"2022-09-30","cited_by_count":13},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10},{"id":"2306.09048","title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","created":"2023-06-15","cited_by_count":8},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4}],"next_cursor":null}