{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"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":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"1805.01934","title":"Learning to See in the Dark","created":"2018-05-04","cited_by_count":460},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2305.14909","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","created":"2023-05-24","cited_by_count":207},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94},{"id":"2012.07277","title":"Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs","created":"2020-12-14","cited_by_count":83},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68},{"id":"2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","created":"2023-03-01","cited_by_count":67},{"id":"1902.03334","title":"Photorealistic Image Synthesis for Object Instance Detection","created":"2019-02-09","cited_by_count":66},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2403.11552","title":"LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning","created":"2024-03-18","cited_by_count":63},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54},{"id":"2005.04117","title":"NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results","created":"2020-05-08","cited_by_count":51},{"id":"2407.15272","title":"MIBench: Evaluating Multimodal Large Language Models over Multiple Images","created":"2024-07-21","cited_by_count":39},{"id":"2410.23156","title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","created":"2024-10-30","cited_by_count":39},{"id":"1801.07357","title":"CHALET: Cornell House Agent Learning Environment","created":"2018-01-23","cited_by_count":38},{"id":"2503.18971","title":"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","created":"2025-03-22","cited_by_count":38},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33},{"id":"2005.08230","title":"Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation","created":"2020-05-17","cited_by_count":31},{"id":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30},{"id":"2506.00411","title":"LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks","created":"2025-05-31","cited_by_count":26},{"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":"2409.19250","title":"Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition","created":"2024-09-28","cited_by_count":14},{"id":"2306.01295","title":"Egocentric Planning for Scalable Embodied Task Achievement","created":"2023-06-02","cited_by_count":7},{"id":"2506.14968","title":"FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization","created":"2025-06-17","cited_by_count":7},{"id":"2403.16184","title":"Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement","created":"2024-03-24","cited_by_count":1}],"next_cursor":null}