{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"1903.03911","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","created":"2019-03-10","cited_by_count":119},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2105.02976","title":"LASR: Learning Articulated Shape Reconstruction from a Monocular Video","created":"2021-05-06","cited_by_count":116},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2106.05258","title":"Generative Models as a Data Source for Multiview Representation Learning","created":"2021-06-09","cited_by_count":104},{"id":"2302.06671","title":"GenAug: Retargeting behaviors to unseen situations via Generative Augmentation","created":"2023-02-13","cited_by_count":104},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95},{"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":"2104.03437","title":"CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds","created":"2021-04-08","cited_by_count":84},{"id":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82},{"id":"2007.12868","title":"OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets","created":"2020-07-25","cited_by_count":74},{"id":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"2303.15782","title":"CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects","created":"2023-03-28","cited_by_count":64},{"id":"2310.03602","title":"Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints","created":"2023-10-05","cited_by_count":60},{"id":"2205.03532","title":"Factory: Fast Contact for Robotic Assembly","created":"2022-05-07","cited_by_count":54},{"id":"2205.08525","title":"Self-supervised Neural Articulated Shape and Appearance Models","created":"2022-05-17","cited_by_count":51},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46},{"id":"2311.17261","title":"SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors","created":"2023-11-28","cited_by_count":43},{"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":"2311.00926","title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","created":"2023-11-02","cited_by_count":41},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"1806.06465","title":"The RBO Dataset of Articulated Objects and Interactions","created":"2018-06-17","cited_by_count":34},{"id":"1708.05869","title":"Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications","created":"2017-08-19","cited_by_count":31},{"id":"2310.14197","title":"Diffusion-based Data Augmentation for Nuclei Image Segmentation","created":"2023-10-22","cited_by_count":31},{"id":"2212.04819","title":"Phone2Proc: Bringing Robust Robots Into Our Chaotic World","created":"2022-12-08","cited_by_count":26},{"id":"2110.07911","title":"Learning to Infer Kinematic Hierarchies for Novel Object Instances","created":"2021-10-15","cited_by_count":10},{"id":"2203.10488","title":"Inferring Articulated Rigid Body Dynamics from RGBD Video","created":"2022-03-20","cited_by_count":10},{"id":"2302.10693","title":"Sim2Real$^2$: Actively Building Explicit Physics Model for Precise Articulated Object Manipulation","created":"2023-02-21","cited_by_count":10},{"id":"2305.00348","title":"Modality-invariant Visual Odometry for Embodied Vision","created":"2023-04-29","cited_by_count":6},{"id":"2303.01484","title":"Predicting Motion Plans for Articulating Everyday Objects","created":"2023-03-02","cited_by_count":5},{"id":"2203.04791","title":"Dimensionality Reduction and Prioritized Exploration for Policy Search","created":"2022-03-09","cited_by_count":3}],"next_cursor":null}