{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"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":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168},{"id":"2410.07166","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","created":"2024-10-09","cited_by_count":144},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107},{"id":"2405.17238","title":"IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities","created":"2024-05-27","cited_by_count":103},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"2109.14723","title":"BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief","created":"2021-09-29","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":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"2301.00182","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","created":"2022-12-31","cited_by_count":49},{"id":"1905.01608","title":"PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph","created":"2019-05-05","cited_by_count":44},{"id":"2502.06787","title":"Visual Agentic AI for Spatial Reasoning with a Dynamic API","created":"2025-02-10","cited_by_count":43},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33},{"id":"2309.09182","title":"Optimal Scene Graph Planning with Large Language Model Guidance","created":"2023-09-17","cited_by_count":27},{"id":"2304.13826","title":"Programmatically Grounded, Compositionally Generalizable Robotic Manipulation","created":"2023-04-26","cited_by_count":26},{"id":"2305.03742","title":"Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming","created":"2023-05-05","cited_by_count":18},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18},{"id":"2207.04364","title":"Sequential Manipulation Planning on Scene Graph","created":"2022-07-10","cited_by_count":17},{"id":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16},{"id":"2501.13400","title":"YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review","created":"2025-01-23","cited_by_count":15},{"id":"2405.19793","title":"PDDLEGO: Iterative Planning in Textual Environments","created":"2024-05-30","cited_by_count":14},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13},{"id":"2303.00438","title":"A Framework for Neurosymbolic Robot Action Planning using Large Language Models","created":"2023-03-01","cited_by_count":12},{"id":"2412.14515","title":"Relational Programming with Foundation Models","created":"2024-12-19","cited_by_count":7},{"id":"2411.01284","title":"Task-Oriented Hierarchical Object Decomposition for Visuomotor Control","created":"2024-11-02","cited_by_count":6},{"id":"2503.21937","title":"Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming","created":"2025-03-27","cited_by_count":4}],"next_cursor":null}