{"list":"other","total":69,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"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":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"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":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2305.16867","title":"Playing repeated games with Large Language Models","created":"2023-05-26","cited_by_count":217},{"id":"2309.17288","title":"AutoAgents: A Framework for Automatic Agent Generation","created":"2023-09-29","cited_by_count":216},{"id":"2009.08553","title":"Generation-Augmented Retrieval for Open-domain Question Answering","created":"2020-09-17","cited_by_count":186},{"id":"2308.09592","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","created":"2023-08-18","cited_by_count":183},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"1903.01959","title":"Learning Exploration Policies for Navigation","created":"2019-03-05","cited_by_count":116},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"2312.11865","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","created":"2023-12-19","cited_by_count":79},{"id":"2312.17025","title":"Experiential Co-Learning of Software-Developing Agents","created":"2023-12-28","cited_by_count":57},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54},{"id":"2110.14143","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","created":"2021-10-27","cited_by_count":53},{"id":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51},{"id":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48},{"id":"2007.03669","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","created":"2020-07-07","cited_by_count":43},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39},{"id":"2304.12998","title":"ChatLLM Network: More brains, More intelligence","created":"2023-04-24","cited_by_count":37},{"id":"1808.03405","title":"End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning","created":"2018-08-10","cited_by_count":35},{"id":"2302.06826","title":"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models","created":"2023-02-14","cited_by_count":33},{"id":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","cited_by_count":32},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30},{"id":"1705.10561","title":"End-to-end Active Object Tracking via Reinforcement Learning","created":"2017-05-30","cited_by_count":28},{"id":"2312.02519","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","created":"2023-12-05","cited_by_count":24},{"id":"2403.08282","title":"Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation","created":"2024-03-13","cited_by_count":24},{"id":"2312.01508","title":"CityGen: Infinite and Controllable City Layout Generation","created":"2023-12-03","cited_by_count":22},{"id":"1811.07029","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","created":"2018-11-13","cited_by_count":20},{"id":"2303.00638","title":"MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts","created":"2023-03-01","cited_by_count":18},{"id":"2403.18493","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","created":"2024-03-27","cited_by_count":17},{"id":"2309.03599","title":"Chasing Consistency in Text-to-3D Generation from a Single Image","created":"2023-09-07","cited_by_count":13},{"id":"2312.04819","title":"Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learning","created":"2023-12-08","cited_by_count":11}],"next_cursor":null}