{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"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":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"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":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"1703.02018","title":"Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation","created":"2017-03-06","cited_by_count":90},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"2105.03655","title":"FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding","created":"2021-05-08","cited_by_count":81},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81},{"id":"1908.04929","title":"3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents","created":"2019-08-14","cited_by_count":74},{"id":"2205.02909","title":"RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks","created":"2022-05-05","cited_by_count":72},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68},{"id":"2105.12244","title":"DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting","created":"2021-05-25","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":"2303.13483","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","created":"2023-03-23","cited_by_count":57},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49},{"id":"2012.04293","title":"CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions","created":"2020-12-08","cited_by_count":44},{"id":"2203.17275","title":"DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools","created":"2022-03-31","cited_by_count":44},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44},{"id":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","cited_by_count":40},{"id":"2212.04819","title":"Phone2Proc: Bringing Robust Robots Into Our Chaotic World","created":"2022-12-08","cited_by_count":26},{"id":"2302.11553","title":"RoboNinja: Learning an Adaptive Cutting Policy for Multi-Material Objects","created":"2023-02-22","cited_by_count":21},{"id":"2306.12392","title":"One-shot Imitation Learning via Interaction Warping","created":"2023-06-21","cited_by_count":16},{"id":"2304.14389","title":"SLoMo: A General System for Legged Robot Motion Imitation from Casual Videos","created":"2023-04-27","cited_by_count":12},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","cited_by_count":12},{"id":"2210.15751","title":"Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation","created":"2022-10-27","cited_by_count":10},{"id":"2303.08135","title":"Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations","created":"2023-03-14","cited_by_count":10},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8}],"next_cursor":null}