{"list":"other","total":74,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"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":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"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":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"1705.08080","title":"Visual Semantic Planning using Deep Successor Representations","created":"2017-05-23","cited_by_count":45},{"id":"2305.05252","title":"Distilling Script Knowledge from Large Language Models for Constrained Language Planning","created":"2023-05-09","cited_by_count":45},{"id":"1903.00784","title":"Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents","created":"2019-03-02","cited_by_count":44},{"id":"2212.08681","title":"Plansformer: Generating Symbolic Plans using Transformers","created":"2022-12-16","cited_by_count":41},{"id":"2401.12975","title":"HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments","created":"2024-01-23","cited_by_count":32},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28},{"id":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23},{"id":"2210.04964","title":"Generating Executable Action Plans with Environmentally-Aware Language Models","created":"2022-10-10","cited_by_count":21},{"id":"2108.06038","title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","created":"2021-08-13","cited_by_count":17},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14},{"id":"2312.03395","title":"Diffused Task-Agnostic Milestone Planner","created":"2023-12-06","cited_by_count":12}],"next_cursor":null}