{"list":"other","total":52,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"1907.13528","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","created":"2019-07-31","cited_by_count":320},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"2305.16867","title":"Playing repeated games with Large Language Models","created":"2023-05-26","cited_by_count":217},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172},{"id":"2308.13067","title":"Causal Parrots: Large Language Models May Talk Causality But Are Not Causal","created":"2023-08-24","cited_by_count":150},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"2212.05206","title":"Thinking Fast and Slow in Large Language Models","created":"2022-12-10","cited_by_count":137},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70},{"id":"1603.01312","title":"Learning Physical Intuition of Block Towers by Example","created":"2016-03-03","cited_by_count":68},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2311.09247","title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","created":"2023-11-14","cited_by_count":55},{"id":"1901.08162","title":"Causal Reasoning from Meta-reinforcement Learning","created":"2019-01-23","cited_by_count":53},{"id":"2304.13187","title":"AI-assisted coding: Experiments with GPT-4","created":"2023-04-25","cited_by_count":43},{"id":"1901.06085","title":"Theory of Minds: Understanding Behavior in Groups Through Inverse Planning","created":"2019-01-18","cited_by_count":30},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20},{"id":"2206.08353","title":"Towards Understanding How Machines Can Learn Causal Overhypotheses","created":"2022-06-16","cited_by_count":14},{"id":"1609.04212","title":"Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning","created":"2016-09-14","cited_by_count":12},{"id":"1809.01524","title":"Modeling human intuitions about liquid flow with particle-based simulation","created":"2018-09-05","cited_by_count":12},{"id":"2305.17023","title":"Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?","created":"2023-05-26","cited_by_count":10},{"id":"2208.02914","title":"Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind","created":"2022-08-04","cited_by_count":9},{"id":"2302.04536","title":"Better by you, better than me, chatgpt3 as writing assistance in students essays","created":"2023-02-09","cited_by_count":9},{"id":"2204.03592","title":"Testing the limits of natural language models for predicting human language judgments","created":"2022-04-07","cited_by_count":7},{"id":"2310.19943","title":"The Acquisition of Physical Knowledge in Generative Neural Networks","created":"2023-10-30","cited_by_count":3}],"next_cursor":null}