{"list":"other","total":70,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"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":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"2305.13626","title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","created":"2023-05-23","cited_by_count":116},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1706.08502","title":"Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog","created":"2017-06-26","cited_by_count":86},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2311.00262","title":"Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents","created":"2023-11-01","cited_by_count":77},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"2309.14320","title":"MUTEX: Learning Unified Policies from Multimodal Task Specifications","created":"2023-09-25","cited_by_count":70},{"id":"1910.03655","title":"Executing Instructions in Situated Collaborative Interactions","created":"2019-10-08","cited_by_count":69},{"id":"2305.02750","title":"A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects","created":"2023-05-04","cited_by_count":66},{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56},{"id":"2112.03763","title":"Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning","created":"2021-12-07","cited_by_count":40},{"id":"2402.12914","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","created":"2024-02-20","cited_by_count":38},{"id":"2110.15349","title":"Learning to Ground Multi-Agent Communication with Autoencoders","created":"2021-10-28","cited_by_count":37},{"id":"2305.04147","title":"Controllable Mixed-Initiative Dialogue Generation through Prompting","created":"2023-05-06","cited_by_count":32},{"id":"2410.06237","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","created":"2024-10-08","cited_by_count":32},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30},{"id":"2211.09935","title":"CAPE: Corrective Actions from Precondition Errors using Large Language Models","created":"2022-11-17","cited_by_count":30},{"id":"2111.03205","title":"LILA: Language-Informed Latent Actions","created":"2021-11-05","cited_by_count":27},{"id":"1903.00122","title":"Improving Grounded Natural Language Understanding through Human-Robot Dialog","created":"2019-03-01","cited_by_count":25},{"id":"2310.01824","title":"Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI","created":"2023-10-03","cited_by_count":23},{"id":"2405.10020","title":"Natural Language Can Help Bridge the Sim2Real Gap","created":"2024-05-16","cited_by_count":21},{"id":"1906.10187","title":"Learning to Interactively Learn and Assist","created":"2019-06-24","cited_by_count":20},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19},{"id":"2303.01586","title":"Alexa Arena: A User-Centric Interactive Platform for Embodied AI","created":"2023-03-02","cited_by_count":18},{"id":"2210.04476","title":"Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks","created":"2022-10-10","cited_by_count":17},{"id":"2409.02645","title":"Emergent Language: A Survey and Taxonomy","created":"2024-09-04","cited_by_count":13},{"id":"2112.08351","title":"Database Search Results Disambiguation for Task-Oriented Dialog Systems","created":"2021-12-15","cited_by_count":10},{"id":"2204.04687","title":"MA-Dreamer: Coordination and communication through shared imagination","created":"2022-04-10","cited_by_count":6},{"id":"2203.07478","title":"Synergistic Scheduling of Learning and Allocation of Tasks in Human-Robot Teams","created":"2022-03-14","cited_by_count":5},{"id":"2406.05003","title":"Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems","created":"2024-06-07","cited_by_count":4},{"id":"1405.7711","title":"Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language","created":"2014-01-16","cited_by_count":3},{"id":"2303.07265","title":"Multimodal Reinforcement Learning for Robots Collaborating with Humans","created":"2023-03-13","cited_by_count":3},{"id":"2403.16178","title":"Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation","created":"2024-03-24","cited_by_count":2},{"id":"2006.00882","title":"Should artificial agents ask for help in human-robot collaborative problem-solving?","created":"2020-05-25","cited_by_count":1},{"id":"2110.03071","title":"Two Many Cooks: Understanding Dynamic Human-Agent Team Communication and Perception Using Overcooked 2","created":"2021-10-06","cited_by_count":1},{"id":"2305.15288","title":"Concurrent Constrained Optimization of Unknown Rewards for Multi-Robot Task Allocation","created":"2023-05-24","cited_by_count":1}],"next_cursor":null}