{"list":"other","total":67,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","created":"2019-01-07","cited_by_count":192},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"2206.08896","title":"Evolution through Large Models","created":"2022-06-17","cited_by_count":134},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126},{"id":"2310.19046","title":"Large Language Models as Evolutionary Optimizers","created":"2023-10-29","cited_by_count":124},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96},{"id":"2501.11120","title":"Tell me about yourself: LLMs are aware of their learned behaviors","created":"2025-01-19","cited_by_count":91},{"id":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47},{"id":"2310.13032","title":"Quality-Diversity through AI Feedback","created":"2023-10-19","cited_by_count":40},{"id":"1806.01186","title":"Penalizing side effects using stepwise relative reachability","created":"2018-06-04","cited_by_count":38},{"id":"2310.15127","title":"Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models","created":"2023-10-23","cited_by_count":37},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34},{"id":"2306.00323","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","created":"2023-06-01","cited_by_count":30},{"id":"2402.09764","title":"Aligning Crowd Feedback via Distributional Preference Reward Modeling","created":"2024-02-15","cited_by_count":28},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20},{"id":"1906.05175","title":"Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites","created":"2019-06-12","cited_by_count":18},{"id":"2311.00344","title":"A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents","created":"2023-11-01","cited_by_count":18},{"id":"2006.07495","title":"Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity","created":"2020-06-12","cited_by_count":15},{"id":"2302.00463","title":"Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains","created":"2023-02-01","cited_by_count":13},{"id":"2402.12590","title":"Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation","created":"2024-02-19","cited_by_count":13},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11},{"id":"1909.04430","title":"An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended Evolution II Special Issue","created":"2019-09-10","cited_by_count":10},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8},{"id":"2406.04663","title":"LLM-POET: Evolving Complex Environments using Large Language Models","created":"2024-06-07","cited_by_count":5},{"id":"2403.16649","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","created":"2024-03-25","cited_by_count":3},{"id":"2002.11174","title":"TanksWorld: A Multi-Agent Environment for AI Safety Research","created":"2020-02-25","cited_by_count":2},{"id":"2011.13880","title":"REAL-X -- Robot open-Ended Autonomous Learning Architectures: Achieving Truly End-to-End Sensorimotor Autonomous Learning Systems","created":"2020-11-27","cited_by_count":2},{"id":"2403.07182","title":"MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains","created":"2024-03-11","cited_by_count":2},{"id":"2409.13315","title":"Exploring the Performance-Reproducibility Trade-off in Quality-Diversity","created":"2024-09-20","cited_by_count":2}],"next_cursor":null}