{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2312.14135","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","created":"2023-12-21","cited_by_count":482},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138},{"id":"2404.07103","title":"Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs","created":"2024-04-10","cited_by_count":119},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"1904.09503","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","created":"2019-04-20","cited_by_count":98},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53},{"id":"2305.16582","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","created":"2023-05-26","cited_by_count":52},{"id":"2405.01534","title":"Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks","created":"2024-05-02","cited_by_count":52},{"id":"2305.14985","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models","created":"2023-05-24","cited_by_count":47},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46},{"id":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36},{"id":"2211.03267","title":"Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following","created":"2022-11-07","cited_by_count":33},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29},{"id":"2409.09345","title":"Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models","created":"2024-09-14","cited_by_count":28},{"id":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24},{"id":"2403.02628","title":"Interactive Continual Learning: Fast and Slow Thinking","created":"2024-03-05","cited_by_count":23},{"id":"2311.04901","title":"GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs","created":"2023-11-08","cited_by_count":18},{"id":"2310.02264","title":"Generalizable Long-Horizon Manipulations with Large Language Models","created":"2023-10-03","cited_by_count":16},{"id":"2402.09838","title":"Performative Reinforcement Learning in Gradually Shifting Environments","created":"2024-02-15","cited_by_count":14},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13},{"id":"2310.18127","title":"Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models","created":"2023-10-27","cited_by_count":9},{"id":"2302.09368","title":"Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation","created":"2023-02-18","cited_by_count":7},{"id":"2405.08997","title":"LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages","created":"2024-05-14","cited_by_count":6},{"id":"2407.19630","title":"LLMs' Understanding of Natural Language Revealed","created":"2024-07-29","cited_by_count":6},{"id":"2412.11484","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","created":"2024-12-16","cited_by_count":6},{"id":"2309.12529","title":"Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution","created":"2023-09-21","cited_by_count":5},{"id":"2303.07622","title":"RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback","created":"2023-03-14","cited_by_count":3}],"next_cursor":null}