{"list":"other","total":79,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"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":"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":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2302.10663","title":"RealFusion: 360{\\deg} Reconstruction of Any Object from a Single Image","created":"2023-02-21","cited_by_count":306},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2303.08133","title":"MeshDiffusion: Score-based Generative 3D Mesh Modeling","created":"2023-03-14","cited_by_count":199},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2111.03043","title":"A System for General In-Hand Object Re-Orientation","created":"2021-11-04","cited_by_count":165},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"1903.11239","title":"TossingBot: Learning to Throw Arbitrary Objects with Residual Physics","created":"2019-03-27","cited_by_count":137},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133},{"id":"2110.05113","title":"Learning High-Speed Flight in the Wild","created":"2021-10-11","cited_by_count":128},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111},{"id":"2210.02438","title":"DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics","created":"2022-10-05","cited_by_count":106},{"id":"2105.03655","title":"FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding","created":"2021-05-08","cited_by_count":81},{"id":"2006.05768","title":"Deep Drone Acrobatics","created":"2020-06-10","cited_by_count":75},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66},{"id":"2105.12244","title":"DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting","created":"2021-05-25","cited_by_count":64},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64},{"id":"2105.10389","title":"Learning Visible Connectivity Dynamics for Cloth Smoothing","created":"2021-05-21","cited_by_count":62},{"id":"2111.05623","title":"FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy","created":"2021-11-10","cited_by_count":54},{"id":"2211.09006","title":"ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds","created":"2022-11-16","cited_by_count":54},{"id":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45},{"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":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","cited_by_count":40},{"id":"1405.5848","title":"Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs","created":"2014-05-22","cited_by_count":39},{"id":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","cited_by_count":39},{"id":"1911.04679","title":"Object-Centric Task and Motion Planning in Dynamic Environments","created":"2019-11-12","cited_by_count":35},{"id":"2011.06464","title":"3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators","created":"2020-11-12","cited_by_count":21},{"id":"2302.11553","title":"RoboNinja: Learning an Adaptive Cutting Policy for Multi-Material Objects","created":"2023-02-22","cited_by_count":21},{"id":"2303.09555","title":"SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments","created":"2023-03-16","cited_by_count":20},{"id":"2306.12372","title":"One Policy to Dress Them All: Learning to Dress People with Diverse Poses and Garments","created":"2023-06-21","cited_by_count":19},{"id":"2112.03386","title":"Guided Imitation of Task and Motion Planning","created":"2021-12-06","cited_by_count":18},{"id":"2304.09302","title":"CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation","created":"2023-04-18","cited_by_count":18},{"id":"2201.11924","title":"Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation","created":"2022-01-28","cited_by_count":16},{"id":"2208.05632","title":"Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactions","created":"2022-08-11","cited_by_count":5}],"next_cursor":null}