{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1703.01925","title":"Grammar Variational Autoencoder","created":"2017-03-06","cited_by_count":285},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2307.07162","title":"Drive Like a Human: Rethinking Autonomous Driving with Large Language Models","created":"2023-07-14","cited_by_count":160},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"2301.12050","title":"Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling","created":"2023-01-28","cited_by_count":88},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2306.04891","title":"In-Context Learning through the Bayesian Prism","created":"2023-06-08","cited_by_count":83},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68},{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66},{"id":"2312.05230","title":"Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning","created":"2023-12-08","cited_by_count":60},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52},{"id":"2310.08582","title":"Tree-Planner: Efficient Close-loop Task Planning with Large Language Models","created":"2023-10-12","cited_by_count":48},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44},{"id":"2304.09960","title":"A Latent Space Theory for Emergent Abilities in Large Language Models","created":"2023-04-19","cited_by_count":43},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41},{"id":"2310.10645","title":"Interactive Task Planning with Language Models","created":"2023-10-16","cited_by_count":37},{"id":"2209.00465","title":"On Grounded Planning for Embodied Tasks with Language Models","created":"2022-08-29","cited_by_count":33},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31},{"id":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26}],"next_cursor":null}