{"list":"other","total":57,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"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":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"1802.08802","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","created":"2018-02-24","cited_by_count":284},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2002.04087","title":"Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy","created":"2020-02-10","cited_by_count":183},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2308.05960","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","created":"2023-08-11","cited_by_count":84},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76},{"id":"2310.05418","title":"Humanoid Agents: Platform for Simulating Human-like Generative Agents","created":"2023-10-09","cited_by_count":73},{"id":"2210.13669","title":"Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing","created":"2022-10-25","cited_by_count":71},{"id":"2310.15100","title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","created":"2023-10-23","cited_by_count":70},{"id":"2209.08655","title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","created":"2022-09-18","cited_by_count":66},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62},{"id":"2202.02312","title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","created":"2022-02-04","cited_by_count":61},{"id":"1812.09195","title":"Learning to Navigate the Web","created":"2018-12-21","cited_by_count":60},{"id":"2101.04893","title":"Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels","created":"2021-01-13","cited_by_count":58},{"id":"2308.03427","title":"TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage","created":"2023-08-07","cited_by_count":55},{"id":"2310.02424","title":"AXNav: Replaying Accessibility Tests from Natural Language","created":"2023-10-03","cited_by_count":31},{"id":"2310.08740","title":"A Zero-Shot Language Agent for Computer Control with Structured Reflection","created":"2023-10-12","cited_by_count":28},{"id":"2312.11190","title":"VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning","created":"2023-12-18","cited_by_count":28},{"id":"2406.07739","title":"UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback","created":"2024-06-11","cited_by_count":27},{"id":"2312.01797","title":"LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics","created":"2023-12-04","cited_by_count":26},{"id":"2312.09007","title":"LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution","created":"2023-12-14","cited_by_count":24},{"id":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14},{"id":"2401.14268","title":"GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning","created":"2024-01-25","cited_by_count":14},{"id":"2402.14261","title":"Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming","created":"2024-02-22","cited_by_count":13},{"id":"2308.10435","title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","created":"2023-08-21","cited_by_count":9},{"id":"2310.00091","title":"Towards Automated Accessibility Report Generation for Mobile Apps","created":"2023-09-29","cited_by_count":5}],"next_cursor":null}