{"list":"other","total":95,"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":"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"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":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"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":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"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":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"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":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"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":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2402.01817","title":"LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks","created":"2024-02-02","cited_by_count":179},{"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":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"2301.13166","title":"ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation","created":"2023-01-30","cited_by_count":127},{"id":"2204.03514","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","created":"2022-04-07","cited_by_count":117},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1910.14442","title":"Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments","created":"2019-10-30","cited_by_count":90},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"2311.02873","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","created":"2023-11-06","cited_by_count":81},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75},{"id":"2104.04112","title":"Auxiliary Tasks and Exploration Enable ObjectNav","created":"2021-04-08","cited_by_count":74},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2007.11018","title":"Learning Object Relation Graph and Tentative Policy for Visual Navigation","created":"2020-07-21","cited_by_count":64},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"2305.07154","title":"Foundations of Spatial Perception for Robotics: Hierarchical Representations and Real-time Systems","created":"2023-05-11","cited_by_count":60},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"2106.15648","title":"Learning to Map for Active Semantic Goal Navigation","created":"2021-06-29","cited_by_count":50},{"id":"2008.07792","title":"ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation","created":"2020-08-18","cited_by_count":49},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41},{"id":"2309.00966","title":"Compositional Diffusion-Based Continuous Constraint Solvers","created":"2023-09-02","cited_by_count":40},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"1609.09025","title":"Learning to Push by Grasping: Using multiple tasks for effective learning","created":"2016-09-28","cited_by_count":37},{"id":"2008.12664","title":"Next-Best View Policy for 3D Reconstruction","created":"2020-08-28","cited_by_count":35},{"id":"2202.11907","title":"Uncertainty-driven Planner for Exploration and Navigation","created":"2022-02-24","cited_by_count":33},{"id":"2203.07359","title":"Stubborn: A Strong Baseline for Indoor Object Navigation","created":"2022-03-14","cited_by_count":32},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31},{"id":"2007.12640","title":"Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs","created":"2020-07-24","cited_by_count":30},{"id":"1406.5670","title":"3D ShapeNets: A Deep Representation for Volumetric Shapes","created":"2014-06-22","cited_by_count":27},{"id":"2304.13826","title":"Programmatically Grounded, Compositionally Generalizable Robotic Manipulation","created":"2023-04-26","cited_by_count":26},{"id":"2312.11713","title":"Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies","created":"2023-12-18","cited_by_count":25},{"id":"2210.15185","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","created":"2022-10-27","cited_by_count":22},{"id":"2212.02497","title":"PEANUT: Predicting and Navigating to Unseen Targets","created":"2022-12-05","cited_by_count":22},{"id":"2210.07505","title":"Learning Active Camera for Multi-Object Navigation","created":"2022-10-14","cited_by_count":21},{"id":"2307.10079","title":"Scientific Exploration of Challenging Planetary Analog Environments with a Team of Legged Robots","created":"2023-07-19","cited_by_count":20},{"id":"2207.04364","title":"Sequential Manipulation Planning on Scene Graph","created":"2022-07-10","cited_by_count":17},{"id":"2103.16095","title":"Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments","created":"2021-03-30","cited_by_count":15},{"id":"2203.10113","title":"Online Next-Best-View Planner for 3D-Exploration and Inspection With a Mobile Manipulator Robot","created":"2022-03-18","cited_by_count":14},{"id":"2003.06734","title":"Active Perception and Representation for Robotic Manipulation","created":"2020-03-15","cited_by_count":10},{"id":"2210.12806","title":"Active Exploration for Robotic Manipulation","created":"2022-10-23","cited_by_count":10},{"id":"2310.00433","title":"Active-Perceptive Motion Generation for Mobile Manipulation","created":"2023-09-30","cited_by_count":10},{"id":"2012.04263","title":"Towards Accurate Active Camera Localization","created":"2020-12-08","cited_by_count":9},{"id":"2109.09323","title":"A Shadowcasting-Based Next-Best-View Planner for Autonomous 3D Exploration","created":"2021-09-20","cited_by_count":9},{"id":"2311.03293","title":"Learning Reusable Manipulation Strategies","created":"2023-11-06","cited_by_count":9},{"id":"2206.08185","title":"UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT","created":"2022-06-16","cited_by_count":7},{"id":"2008.07157","title":"Where to Map? Iterative Rover-Copter Path Planning for Mars Exploration","created":"2020-08-17","cited_by_count":6},{"id":"2205.08325","title":"GraphMapper: Efficient Visual Navigation by Scene Graph Generation","created":"2022-05-17","cited_by_count":6},{"id":"2302.13375","title":"Perceiving Unseen 3D Objects by Poking the Objects","created":"2023-02-26","cited_by_count":5},{"id":"2103.02789","title":"Learning the Next Best View for 3D Point Clouds via Topological Features","created":"2021-03-04","cited_by_count":4},{"id":"2312.13219","title":"Interactive Visual Task Learning for Robots","created":"2023-12-20","cited_by_count":3}],"next_cursor":null}