{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"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":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"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":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"1706.02262","title":"InfoVAE: Information Maximizing Variational Autoencoders","created":"2017-06-07","cited_by_count":124},{"id":"1901.05534","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","created":"2019-01-16","cited_by_count":124},{"id":"2012.00619","title":"We are More than Our Joints: Predicting how 3D Bodies Move","created":"2020-12-01","cited_by_count":115},{"id":"2108.10399","title":"Learning Motion Priors for 4D Human Body Capture in 3D Scenes","created":"2021-08-23","cited_by_count":98},{"id":"2101.06547","title":"LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving","created":"2021-01-16","cited_by_count":96},{"id":"1812.00971","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","created":"2018-12-03","cited_by_count":93},{"id":"2112.10103","title":"SAGA: Stochastic Whole-Body Grasping with Contact","created":"2021-12-19","cited_by_count":91},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"1802.02550","title":"Semi-Amortized Variational Autoencoders","created":"2018-02-07","cited_by_count":83},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"1808.08473","title":"Human-centric Indoor Scene Synthesis Using Stochastic Grammar","created":"2018-08-25","cited_by_count":74},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2104.09194","title":"Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator","created":"2021-04-19","cited_by_count":71},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70},{"id":"2206.05895","title":"Latent Diffusion Energy-Based Model for Interpretable Text Modeling","created":"2022-06-13","cited_by_count":67},{"id":"2007.11018","title":"Learning Object Relation Graph and Tentative Policy for Visual Navigation","created":"2020-07-21","cited_by_count":64},{"id":"2206.13387","title":"ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning","created":"2022-06-18","cited_by_count":64},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57},{"id":"2210.00722","title":"GenDexGrasp: Generalizable Dexterous Grasping","created":"2022-10-03","cited_by_count":56},{"id":"1910.04586","title":"Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles","created":"2019-10-10","cited_by_count":51},{"id":"1711.06391","title":"Data-driven Planning via Imitation Learning","created":"2017-11-17","cited_by_count":36},{"id":"2007.09841","title":"Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation","created":"2020-07-20","cited_by_count":34},{"id":"1704.00112","title":"Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars","created":"2017-04-01","cited_by_count":25},{"id":"2007.14545","title":"Learning Object-conditioned Exploration using Distributed Soft Actor Critic","created":"2020-07-29","cited_by_count":12},{"id":"2008.05570","title":"PLACE: Proximity Learning of Articulation and Contact in 3D Environments","created":"2020-08-12","cited_by_count":10},{"id":"1904.01698","title":"VRGym: A Virtual Testbed for Physical and Interactive AI","created":"2019-04-02","cited_by_count":9},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7}],"next_cursor":null}